In [16]:
import random
import math
from environment import Agent, Environment
from planner import RoutePlanner
from simulator import Simulator
# import numpy as np

class LearningAgent(Agent):
    """ An agent that learns to drive in the Smartcab world.
        This is the object you will be modifying. """ 

    def __init__(self, env, learning=False, epsilon=1.0, alpha=0.5):
        super(LearningAgent, self).__init__(env)     # Set the agent in the evironment 
        self.planner = RoutePlanner(self.env, self)  # Create a route planner
        self.valid_actions = self.env.valid_actions  # The set of valid actions

        # Set parameters of the learning agent
        self.learning = learning # Whether the agent is expected to learn
        self.Q = dict()          # Create a Q-table which will be a dictionary of tuples
        self.epsilon = epsilon   # Random exploration factor
        self.alpha = alpha       # Learning factor

        ###########
        ## TO DO ##
        ###########
        # Set any additional class parameters as needed
        self.trial = 0.0



    def reset(self, destination=None, testing=True):
        """ The reset function is called at the beginning of each trial.
            'testing' is set to True if testing trials are being used
            once training trials have completed. """

        # Select the destination as the new location to route to
        self.planner.route_to(destination)
        
        ########### 
        ## TO DO ##
        ###########
        # Update epsilon using a decay function of your choice
        # Update additional class parameters as needed
        # If 'testing' is True, set epsilon and alpha to 0
                # If 'testing' is True, set epsilon and alpha to 0
#         if testing==True:
#             self.epsilon = 0.0 
#             self.alpha = 0.0
#         else:
#             if testing ==False and self.trial<=10.0:
#                 self.alpha = .5
#                 self.trial = 10.0
#                 self.epsilon = self.epsilon 
#                 self.epsilon = 0.8 *.97
#             if testing == False and self.trial ==12.0:
#                 self.trial >=12.0
#                 self.epsilon= self.epsilon
#                 self.epsilon = .5*.96
#                 self.alpha = .5
#                 self.epsilon = 1/self.trial**2.0
#             if  testing ==False and self.trial>=15.0:
#                 self.alpha = .5
#                 self.trial = self.trial
#                 self.epsilon = np.cos(self.alpha*self.trial)
#             if  testing == False and self.trial <= 20.0:
#                 self.trial = self.trial
#                 self.alpha = .5
#                 self.epsilon += np.exp(-1*(self.alpha*self.trial))

        self.alpha = 0.015

        self.trial = self.trial+1

        if testing==True:
            self.epsilon = 0.0 
            self.alpha = 0.0
        elif testing == False:
#             self.epsilon = self.epsilon - .05
#             self.alpha = .5
#             self.trial += 1.0
#             self.epsilon = self.epsilon 
#             self.epsilon = self.epsilon*.25
#             self.epsilon = self.alpha**self.trial
#             self.epsilon = 1.0/self.trial**2.0
#             self.epsilon = np.cos(self.alpha*self.trial)
#             self.epsilon = np.exp(-1*(self.alpha*self.trial))
            self.epsilon = math.exp(-(self.alpha*self.trial))           
        
        return None

    def build_state(self):
        """ The build_state function is called when the agent requests data from the 
            environment. The next waypoint, the intersection inputs, and the deadline 
            are all features available to the agent. """

        # Collect data about the environment
        waypoint = self.planner.next_waypoint() # The next waypoint 
        inputs = self.env.sense(self)           # Visual input - intersection light and traffic
        deadline = self.env.get_deadline(self)  # Remaining deadline
        

        ########### 
        ## TO DO ##
        ###########
        
        # NOTE : you are not allowed to engineer eatures outside of the inputs available.
        # Because the aim of this project is to teach Reinforcement Learning, we have placed 
        # constraints in order for you to learn how to adjust epsilon and alpha, and thus learn about the balance between exploration and exploitation.
        # With the hand-engineered features, this learning process gets entirely negated.
        
        # Set 'state' as a tuple of relevant data for the agent        
       
        state = waypoint, inputs['light'], inputs['oncoming'], inputs['left']
#         if self.learning == True:
#             if state not in self.Q.keys():
#                 self.createQ(state)
#             else:
#                 state.learning ==False

        if self.learning ==True:
            self.createQ(state)

        return state

    def get_maxQ(self, state):
        """ The get_max_Q function is called when the agent is asked to find the
            maximum Q-value of all actions based on the 'state' the smartcab is in. """

        ########### 
        ## TO DO ##
        ###########
        # Calculate the maximum Q-value of all actions for a given state
#         state = self.Q[state][action]

#         max = max(state, key = lambda x: state[x])
#         for action in state:

#             maxQ <= self.Q[state][action]:
#                maxQ = self.Q(state[max] and [action])
        maxQ = max(self.Q[state].values())

        return maxQ 

    def createQ(self, state):
        """ The createQ function is called when a state is generated by the agent. """

        ########### 
        ## TO DO ##
        ###########
        # When learning, check if the 'state' is not in the Q-table
        # If it is not, create a new dictionary for that state
        #   Then, for each action available, set the initial Q-value to 0.0

#         if not self.learning:
#             state = self.valid_actions(state,{'left':0.0,'oncoming':0.25,'forward':0.25,'right':0.0}) #'None','forward'

#         if self.learning == True and state not in self.Q:
#             self.Q[state]={key: 0 for key in self.valid_actions}

        if self.learning==True and state not in self.Q:

            self.Q[state] = {action: 0 for action in self.valid_actions}

        return




    def choose_action(self, state):
        """ The choose_action function is called when the agent is asked to choose
            which action to take, based on the 'state' the smartcab is in. """

        # Set the agent state and default action
        self.state = state
        self.next_waypoint = self.planner.next_waypoint()
        action = None

        ########### 
        ## TO DO ##
        ###########
        # When not learning, choose a random action
        # When learning, choose a random action with 'epsilon' probability
        # Otherwise, choose an action with the highest Q-value for the current state
        # Be sure that when choosing an action with highest Q-value that you randomly select between actions that "tie".
        if self.learning:

            if self.epsilon > random.random():
                action = random.choice(self.valid_actions)

            else:
                maxQ = self.get_maxQ(state)
                action = random.choice([action for action in self.valid_actions if self.Q[state][action]==maxQ])

        if self.learning==False:

            action = random.choice(self.valid_actions)
        return action


    def learn(self, state, action, reward):
        """ The learn function is called after the agent completes an action and
            receives a reward. This function does not consider future rewards 
            when conducting learning. """

        ########### 
        ## TO DO ##
        ###########
        # When learning, implement the value iteration update rule
        #   Use only the learning rate 'alpha' (do not use the discount factor 'gamma')

        if self.learning == True:
            self.Q[state][action] = (1 - self.alpha) * self.Q[state][action] + self.alpha * reward
#         if self.learning==True:
#             self.Q[state][action] = self.alpha*(reward-self.Q[state][action])
    

        return


    def update(self):
        """ The update function is called when a time step is completed in the 
            environment for a given trial. This function will build the agent
            state, choose an action, receive a reward, and learn if enabled. """

        state = self.build_state()          # Get current state
        self.createQ(state)                 # Create 'state' in Q-table
        action = self.choose_action(state)  # Choose an action
        reward = self.env.act(self, action) # Receive a reward
        self.learn(state, action, reward)   # Q-learn

        return
        

def run():
    """ Driving function for running the simulation. 
        Press ESC to close the simulation, or [SPACE] to pause the simulation. """

    ##############
    # Create the environment
    # Flags:
    #   verbose     - set to True to display additional output from the simulation
    #   num_dummies - discrete number of dummy agents in the environment, default is 100
    #   grid_size   - discrete number of intersections (columns, rows), default is (8, 6)
    env = Environment(verbose=True)
    
    ##############
    # Create the driving agent
    # Flags:
    #   learning   - set to True to force the driving agent to use Q-learning
    #    * epsilon - continuous value for the exploration factor, default is 1
    #    * alpha   - continuous value for the learning rate, default is 0.5
    agent = env.create_agent(LearningAgent, learning=True)#,alpha = .6,epsilon=.75
    
    ##############
    # Follow the driving agent
    # Flags:
    #   enforce_deadline - set to True to enforce a deadline metric
    env.set_primary_agent(agent,enforce_deadline=True)

    ##############
    # Create the simulation
    # Flags:
    #   update_delay - continuous time (in seconds) between actions, default is 2.0 seconds
    #   display      - set to False to disable the GUI if PyGame is enabled
    #   log_metrics  - set to True to log trial and simulation results to /logs
    #   optimized    - set to True to change the default log file name
    sim = Simulator(env,update_delay=.00015,log_metrics=True,display=False,optimized=True)
    
    ##############
    # Run the simulator
    # Flags:
    #   tolerance  - epsilon tolerance before beginning testing, default is 0.05 
    #   n_test     - discrete number of testing trials to perform, default is 0
    sim.run(n_test=20, tolerance =.02)#tolerance=.02


if __name__ == '__main__':
    run()
/-------------------------
| Training trial 1
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (2, 4), deadline = 30
Simulating trial. . . 
epsilon = 0.9851; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: 2.30655995489
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 2.30655995489312, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.31)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: forward, reward: -39.689998042
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 29, 't': 1, 'action': 'forward', 'reward': -39.68999804201234, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.69)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: forward, reward: -10.0171275884
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': -10.017127588380944, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.02)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: left, reward: -40.1061544576
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': 'left', 'reward': -40.10615445761635, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.11)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 0.330768816421
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 0.33076881642114697, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.33)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: right, reward: 1.95975434181
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 1.9597543418128451, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.96)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: -4.13347882168
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 24, 't': 6, 'action': None, 'reward': -4.133478821679987, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.13)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: -5.03062622255
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 23, 't': 7, 'action': None, 'reward': -5.0306262225549645, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -5.03)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: left, reward: 1.80719466493
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 22, 't': 8, 'action': 'left', 'reward': 1.8071946649312776, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.81)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 0.551005555711
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 21, 't': 9, 'action': None, 'reward': 0.5510055557113285, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 0.55)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: forward, reward: 0.879540452348
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'right'), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 0.8795404523475125, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'right')
Agent drove forward instead of right. (rewarded 0.88)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: right, reward: 1.95658169342
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 1.9565816934198819, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 1.96)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: None, reward: -4.44686332344
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 18, 't': 12, 'action': None, 'reward': -4.446863323440539, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.45)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: right, reward: 1.46112438566
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 1.461124385655295, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.46)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: None, reward: 2.55070756475
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 14, 'action': None, 'reward': 2.550707564747678, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.55)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: right, reward: 1.40624650719
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 15, 't': 15, 'action': 'right', 'reward': 1.4062465071881576, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove right instead of left. (rewarded 1.41)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: left, reward: -9.70406226555
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': -9.704062265551467, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.70)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: None, reward: 1.02674876815
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 13, 't': 17, 'action': None, 'reward': 1.0267487681520542, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.03)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: forward, reward: -9.28777254574
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'right', 'left'), 'deadline': 12, 't': 18, 'action': 'forward', 'reward': -9.287772545735534, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'left')
Agent attempted driving forward through a red light. (rewarded -9.29)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: forward, reward: -0.00111187396008
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': -0.0011118739600765037, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded -0.00)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: -0.109504991506
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 20, 'action': None, 'reward': -0.10950499150640192, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded -0.11)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: right, reward: 1.30820304003
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'right', 'reward': 1.3082030400348204, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.31)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: forward, reward: -9.5246124462
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 8, 't': 22, 'action': 'forward', 'reward': -9.524612446202175, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.52)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: right, reward: 1.95963835238
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.9596383523784058, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.96)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: left, reward: -9.86532307404
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 6, 't': 24, 'action': 'left', 'reward': -9.865323074038525, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -9.87)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 1.27462097474
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 5, 't': 25, 'action': None, 'reward': 1.2746209747356898, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.27)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: right, reward: -0.27676896616
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 4, 't': 26, 'action': 'right', 'reward': -0.2767689661604009, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded -0.28)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: None, reward: 2.03855535584
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 27, 'action': None, 'reward': 2.0385553558440357, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.04)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: left, reward: 0.498762442416
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 2, 't': 28, 'action': 'left', 'reward': 0.49876244241608414, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 0.50)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 0.786353124052
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 1, 't': 29, 'action': 'right', 'reward': 0.7863531240521637, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 0.79)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 2
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (8, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.9704; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.9704; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.9704; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.9704; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.9704; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: left, reward: -10.4052047625
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': -10.405204762521446, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.41)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 1.83671494582
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.8367149458218062, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.84)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: 1.8722496827
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.8722496826950357, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 1.87)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: right, reward: 2.24946732078
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 2.2494673207755094, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.25)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: left, reward: -20.4747132856
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': -20.474713285606434, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.47)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: left, reward: -19.9831526667
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': -19.983152666693524, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.98)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: None, reward: -4.95191985636
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 14, 't': 6, 'action': None, 'reward': -4.951919856358777, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -4.95)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: right, reward: 0.327329941821
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.32732994182075004, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.33)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: -5.03948879715
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': -5.0394887971471745, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.04)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: right, reward: 1.55965774399
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.5596577439904673, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove right instead of left. (rewarded 1.56)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: left, reward: -40.9192700581
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': -40.919270058136405, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.92)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: 0.222037161565
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.22203716156530096, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent drove right instead of left. (rewarded 0.22)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 1.58723202875
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.5872320287469428, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.59)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: forward, reward: -0.0978244945172
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': -0.0978244945172061, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent drove forward instead of right. (rewarded -0.10)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: -5.40109278527
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 6, 't': 14, 'action': None, 'reward': -5.401092785273204, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.40)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: left, reward: -0.104729378363
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': -0.10472937836258933, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded -0.10)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: left, reward: 0.293404178648
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 0.2934041786481465, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 0.29)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: forward, reward: -9.69538363862
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': -9.695383638617937, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.70)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 0.114102028517
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.11410202851732554, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.11)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: -5.97613605592
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 1, 't': 19, 'action': None, 'reward': -5.976136055922952, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.98)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 3
\-------------------------

Environment.reset(): Trial set up with start = (6, 5), destination = (1, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.9560; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: right, reward: 2.71902067753
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 2.719020677530592, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.72)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 1.59608884685
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.5960888468493344, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.60)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: right, reward: 1.64954968267
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.6495496826701876, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.65)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: forward, reward: -10.9328986632
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': -10.932898663160532, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.93)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: None, reward: -5.25599747039
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': -5.255997470394986, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.26)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: forward, reward: 1.36600754873
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 1.3660075487261323, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove forward instead of left. (rewarded 1.37)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: -19.6434701497
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 19, 't': 6, 'action': 'right', 'reward': -19.643470149685168, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.64)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: forward, reward: -40.4238102744
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': -40.42381027442065, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.42)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 1.35256699004
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.3525669900358674, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.35)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: left, reward: -40.8354261778
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 16, 't': 9, 'action': 'left', 'reward': -40.83542617777636, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.84)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: right, reward: 0.028794712764
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'right'), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 0.02879471276396328, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'right')
Agent drove right instead of left. (rewarded 0.03)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: None, reward: -5.24376641335
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 14, 't': 11, 'action': None, 'reward': -5.243766413348329, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.24)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: right, reward: 1.60803010121
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 1.6080301012061688, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 1.61)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 5), heading: (0, -1), action: forward, reward: 0.0490350027784
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 0.04903500277843831, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove forward instead of right. (rewarded 0.05)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: right, reward: 2.07658719975
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 2.076587199746027, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.08)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: left, reward: -39.1615699217
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 10, 't': 15, 'action': 'left', 'reward': -39.16156992171226, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.16)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: 1.21761257956
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 1.2176125795642905, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.22)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: -9.08510569319
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 17, 'action': 'left', 'reward': -9.085105693192439, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.09)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.0184651885
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 2.0184651885009615, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.02)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: -9.27570033079
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': -9.275700330793427, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -9.28)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: -10.0802828877
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 20, 'action': 'forward', 'reward': -10.080282887714956, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.08)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: right, reward: 0.00864924201037
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 21, 'action': 'right', 'reward': 0.008649242010366875, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.01)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: right, reward: 0.0167668637803
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 3, 't': 22, 'action': 'right', 'reward': 0.01676686378031267, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.02)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: right, reward: -19.047103004
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 2, 't': 23, 'action': 'right', 'reward': -19.047103004043247, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.05)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: -9.02196039511
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 1, 't': 24, 'action': 'forward', 'reward': -9.021960395111947, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.02)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 4
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (7, 5), deadline = 30
Simulating trial. . . 
epsilon = 0.9418; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: -5.3912825297
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 30, 't': 0, 'action': None, 'reward': -5.391282529695494, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -5.39)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: left, reward: 1.32845518059
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 29, 't': 1, 'action': 'left', 'reward': 1.3284551805883567, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent drove left instead of right. (rewarded 1.33)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: left, reward: 1.09978838601
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': 'left', 'reward': 1.099788386010224, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.10)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: -4.51597403573
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 27, 't': 3, 'action': None, 'reward': -4.515974035732632, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.52)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: 2.59597729508
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 2.5959772950788524, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.60)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 1.25577130523
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 25, 't': 5, 'action': None, 'reward': 1.2557713052271318, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.26)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: forward, reward: 2.3369657634
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 2.336965763399367, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.34)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: right, reward: 2.08910851065
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 2.0891085106546052, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.09)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: right, reward: 0.793769421574
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 0.7937694215743069, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.79)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: right, reward: 0.615214409325
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 0.615214409324738, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 0.62)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: forward, reward: -9.22525088128
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': -9.225250881282049, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.23)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: left, reward: 1.57787219491
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 19, 't': 11, 'action': 'left', 'reward': 1.5778721949113077, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent drove left instead of right. (rewarded 1.58)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: left, reward: 2.21542907571
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 12, 'action': 'left', 'reward': 2.215429075711505, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.22)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: right, reward: -0.00536520596642
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': -0.005365205966415099, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded -0.01)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: forward, reward: -39.527194234
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 16, 't': 14, 'action': 'forward', 'reward': -39.52719423402146, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.53)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: forward, reward: -40.7492920747
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 15, 't': 15, 'action': 'forward', 'reward': -40.749292074746215, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.75)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: left, reward: 1.81984242476
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': 1.8198424247611502, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.82)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: right, reward: 1.22945880338
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 1.2294588033776337, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 1.23)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: right, reward: 0.925946629028
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 0.9259466290284253, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.93)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: forward, reward: -39.5711403839
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': -39.571140383853255, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.57)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: None, reward: 1.09997231501
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.0999723150096172, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.10)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: forward, reward: -40.1479040754
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 21, 'action': 'forward', 'reward': -40.147904075447514, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.15)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: left, reward: 0.573633387087
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 22, 'action': 'left', 'reward': 0.5736333870866317, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.57)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 0.806355454714
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 7, 't': 23, 'action': None, 'reward': 0.8063554547144915, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.81)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 1.34279405924
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 6, 't': 24, 'action': None, 'reward': 1.342794059238891, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.34)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: forward, reward: -10.2742104716
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 5, 't': 25, 'action': 'forward', 'reward': -10.274210471640652, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.27)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: left, reward: 0.963368247729
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 4, 't': 26, 'action': 'left', 'reward': 0.9633682477285008, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 0.96)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 0.119528002572
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 3, 't': 27, 'action': 'left', 'reward': 0.11952800257161811, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.12)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: -9.7869558984
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 2, 't': 28, 'action': 'left', 'reward': -9.786955898402377, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.79)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: -5.84301765846
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 1, 't': 29, 'action': None, 'reward': -5.8430176584627675, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.84)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 5
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (4, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.9277; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: -10.505398888
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 30, 't': 0, 'action': 'left', 'reward': -10.50539888795439, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent attempted driving left through a red light. (rewarded -10.51)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: right, reward: 0.324375129095
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 0.3243751290953746, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.32)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 1.89625102112
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.8962510211191193, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.90)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: -4.16850932182
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 27, 't': 3, 'action': None, 'reward': -4.168509321820803, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.17)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: forward, reward: 0.588903303731
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 0.5889033037306631, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove forward instead of right. (rewarded 0.59)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: left, reward: -10.7959039083
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 25, 't': 5, 'action': 'left', 'reward': -10.795903908333068, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.80)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: right, reward: 2.3372919642
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 2.3372919641985535, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.34)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: right, reward: 0.706351505848
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 0.706351505847905, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 0.71)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: left, reward: -10.6978569674
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 22, 't': 8, 'action': 'left', 'reward': -10.697856967362512, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.70)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: left, reward: 1.5650319287
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 21, 't': 9, 'action': 'left', 'reward': 1.5650319287007268, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.57)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: 1.73611541207
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': 1.736115412074212, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 1.74)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: -20.0205850153
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 19, 't': 11, 'action': 'right', 'reward': -20.020585015332856, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.02)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: right, reward: 1.31278027146
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 1.3127802714599948, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.31)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 1.51205759216
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 1.5120575921565778, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.51)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: -0.149290514062
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': -0.14929051406198202, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded -0.15)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: 0.95394385516
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'right'), 'deadline': 15, 't': 15, 'action': 'right', 'reward': 0.9539438551601964, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'right')
Agent followed the waypoint right. (rewarded 0.95)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: -19.2021395051
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': -19.20213950505818, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.20)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: forward, reward: 0.172309007277
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 0.17230900727703857, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded 0.17)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: None, reward: -0.235179638295
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 18, 'action': None, 'reward': -0.2351796382952127, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded -0.24)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: left, reward: 1.55080880092
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 11, 't': 19, 'action': 'left', 'reward': 1.5508088009183152, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.55)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 0.794500499581
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 10, 't': 20, 'action': 'right', 'reward': 0.794500499581053, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 0.79)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: -5.45702108704
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 21, 'action': None, 'reward': -5.457021087036175, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.46)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: left, reward: -19.3951531239
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 8, 't': 22, 'action': 'left', 'reward': -19.39515312390972, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.40)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: right, reward: 0.622075016037
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 0.6220750160374482, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.62)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: right, reward: -0.000349769608283
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 6, 't': 24, 'action': 'right', 'reward': -0.0003497696082834789, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded -0.00)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: 1.61494536797
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 25, 'action': None, 'reward': 1.6149453679652563, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.61)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: forward, reward: -39.3733966472
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 4, 't': 26, 'action': 'forward', 'reward': -39.37339664716772, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.37)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: left, reward: 0.37730526698
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 3, 't': 27, 'action': 'left', 'reward': 0.3773052669797572, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 0.38)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: left, reward: -0.470347324142
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 2, 't': 28, 'action': 'left', 'reward': -0.47034732414152647, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded -0.47)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: left, reward: 0.518922584751
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 1, 't': 29, 'action': 'left', 'reward': 0.5189225847506174, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove left instead of right. (rewarded 0.52)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 6
\-------------------------

Environment.reset(): Trial set up with start = (1, 3), destination = (7, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.9139; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: forward, reward: 0.989335399414
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 0.9893353994139431, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove forward instead of left. (rewarded 0.99)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 1.09173944575
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.0917394457505043, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.09)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: right, reward: 0.207627616639
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.20762761663887896, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.21)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: right, reward: -20.1805868372
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': -20.180586837239744, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.18)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: left, reward: -9.9254920325
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': -9.925492032502746, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -9.93)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: -4.17028179699
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 15, 't': 5, 'action': None, 'reward': -4.170281796993294, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.17)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: right, reward: 0.808489058251
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.8084890582514019, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 0.81)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: left, reward: -39.8630500207
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': -39.86305002070899, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.86)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 1.47275561829
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.4727556182911332, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 1.47)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: forward, reward: 1.68640033252
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.6864003325202306, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent drove forward instead of right. (rewarded 1.69)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: 1.68141517673
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.681415176730754, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.68)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: left, reward: -9.24865962309
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': -9.248659623092095, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.25)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 2.17751260305
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 2.177512603046159, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.18)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: forward, reward: -40.9799799355
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': -40.97997993548518, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.98)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: forward, reward: -39.9561460176
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': -39.95614601764617, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.96)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 2.04235760586
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.042357605863452, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.04)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: -10.9705228677
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': -10.970522867656474, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.97)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 0.507108731226
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 0.5071087312256483, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.51)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: forward, reward: 0.242802285258
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 2, 't': 18, 'action': 'forward', 'reward': 0.24280228525794922, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 0.24)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: forward, reward: -9.85800954355
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': -9.858009543545995, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.86)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 7
\-------------------------

Environment.reset(): Trial set up with start = (5, 5), destination = (1, 2), deadline = 35
Simulating trial. . . 
epsilon = 0.9003; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: left, reward: -9.91650542034
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 35, 't': 0, 'action': 'left', 'reward': -9.916505420338089, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.92)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: forward, reward: -9.47001216133
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 34, 't': 1, 'action': 'forward', 'reward': -9.47001216133041, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.47)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 2.66618091055
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 33, 't': 2, 'action': None, 'reward': 2.6661809105538197, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.67)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: forward, reward: -9.97538906187
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 32, 't': 3, 'action': 'forward', 'reward': -9.975389061874882, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent attempted driving forward through a red light. (rewarded -9.98)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: left, reward: 2.929768164
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 31, 't': 4, 'action': 'left', 'reward': 2.929768164001249, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.93)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 2.82552102901
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 30, 't': 5, 'action': None, 'reward': 2.825521029005314, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.83)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 0.436923389624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 29, 't': 6, 'action': 'right', 'reward': 0.43692338962398036, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.44)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: right, reward: 0.0600491731949
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 28, 't': 7, 'action': 'right', 'reward': 0.06004917319492942, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent drove right instead of forward. (rewarded 0.06)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: -5.08652602056
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 27, 't': 8, 'action': None, 'reward': -5.0865260205649045, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.09)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: right, reward: 1.52567523326
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 26, 't': 9, 'action': 'right', 'reward': 1.5256752332627999, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.53)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: left, reward: 0.582675347587
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 25, 't': 10, 'action': 'left', 'reward': 0.5826753475866618, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.58)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: None, reward: 1.24907598359
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 24, 't': 11, 'action': None, 'reward': 1.249075983586263, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.25)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: right, reward: 1.53597432078
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 23, 't': 12, 'action': 'right', 'reward': 1.5359743207796064, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.54)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: right, reward: -20.3562392119
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 22, 't': 13, 'action': 'right', 'reward': -20.3562392119487, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.36)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: right, reward: 0.847649438341
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 21, 't': 14, 'action': 'right', 'reward': 0.8476494383409222, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.85)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: -4.13727632064
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 15, 'action': None, 'reward': -4.137276320640078, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.14)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: forward, reward: -10.7052776239
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 19, 't': 16, 'action': 'forward', 'reward': -10.705277623919798, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -10.71)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 1.83567147298
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 18, 't': 17, 'action': None, 'reward': 1.8356714729762762, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.84)
49% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: right, reward: 0.685580186309
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 18, 'action': 'right', 'reward': 0.6855801863085618, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 0.69)
46% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: forward, reward: -9.90515802776
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 16, 't': 19, 'action': 'forward', 'reward': -9.905158027763326, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -9.91)
43% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: left, reward: -40.5736246876
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 15, 't': 20, 'action': 'left', 'reward': -40.573624687632396, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.57)
40% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 1.30886790863
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 21, 'action': None, 'reward': 1.3088679086306267, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
37% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: left, reward: 1.24232024513
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 22, 'action': 'left', 'reward': 1.242320245130884, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.24)
34% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: left, reward: -10.0051616269
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 12, 't': 23, 'action': 'left', 'reward': -10.005161626919948, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent attempted driving left through a red light. (rewarded -10.01)
31% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 0.936031565832
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 24, 'action': None, 'reward': 0.9360315658315592, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.94)
29% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: -5.45213762231
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 25, 'action': None, 'reward': -5.452137622310561, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.45)
26% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: left, reward: -20.032639656
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'right', 'right'), 'deadline': 9, 't': 26, 'action': 'left', 'reward': -20.03263965604449, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'right')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.03)
23% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: forward, reward: 0.819963366003
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 8, 't': 27, 'action': 'forward', 'reward': 0.8199633660033826, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove forward instead of left. (rewarded 0.82)
20% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: left, reward: 1.55506835382
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 7, 't': 28, 'action': 'left', 'reward': 1.555068353816111, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.56)
17% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 1.3009490979
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 6, 't': 29, 'action': 'right', 'reward': 1.3009490979018636, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 1.30)
14% of time remaining to reach destination.

/-------------------
| Step 30 Results
\-------------------

Environment.step(): t = 30
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: right, reward: -0.0238831731691
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 30, 'action': 'right', 'reward': -0.023883173169051197, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded -0.02)
11% of time remaining to reach destination.

/-------------------
| Step 31 Results
\-------------------

Environment.step(): t = 31
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 0.738865788681
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 4, 't': 31, 'action': 'right', 'reward': 0.7388657886812771, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.74)
9% of time remaining to reach destination.

/-------------------
| Step 32 Results
\-------------------

Environment.step(): t = 32
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 0.135505608924
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 3, 't': 32, 'action': None, 'reward': 0.13550560892419594, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 0.14)
6% of time remaining to reach destination.

/-------------------
| Step 33 Results
\-------------------

Environment.step(): t = 33
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: forward, reward: -0.103566803467
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 2, 't': 33, 'action': 'forward', 'reward': -0.10356680346726166, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent drove forward instead of right. (rewarded -0.10)
3% of time remaining to reach destination.

/-------------------
| Step 34 Results
\-------------------

Environment.step(): t = 34
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: forward, reward: -40.8947195405
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 1, 't': 34, 'action': 'forward', 'reward': -40.8947195405273, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.89)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 8
\-------------------------

Environment.reset(): Trial set up with start = (4, 4), destination = (6, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.8869; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: left, reward: -19.8654940294
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': -19.865494029379523, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.87)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: -4.59857615923
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': -4.598576159234958, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.60)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: left, reward: 1.34551451117
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.345514511174175, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.35)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: right, reward: 1.61900318291
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.6190031829097737, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 1.62)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.16965503437
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.1696550343700307, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.17)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: 0.48119128481
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 0.4811912848102753, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent drove forward instead of left. (rewarded 0.48)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: 0.947646842395
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.9476468423950246, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.95)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: -4.01346706216
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': -4.013467062159948, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.01)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: left, reward: 1.76848749314
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 1.7684874931390584, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.77)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: left, reward: 0.227558116011
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 0.22755811601113507, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove left instead of forward. (rewarded 0.23)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: left, reward: -10.2665084979
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': -10.266508497910008, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.27)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: None, reward: 1.01477669149
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.0147766914876786, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.01)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: forward, reward: -10.1261960536
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -10.126196053569549, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.13)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: right, reward: 0.799275251373
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.7992752513732684, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.80)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: right, reward: 1.1694609622
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.1694609621960579, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.17)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: forward, reward: -10.4516751708
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -10.451675170750532, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.45)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: right, reward: 0.148170614797
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.14817061479729232, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.15)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 0.621697953466
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 0.621697953465543, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 0.62)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: -40.7940389669
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': 'left', 'reward': -40.794038966853755, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.79)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: -10.1321223425
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': -10.132122342535993, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -10.13)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 9
\-------------------------

Environment.reset(): Trial set up with start = (3, 3), destination = (7, 5), deadline = 30
Simulating trial. . . 
epsilon = 0.8737; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.8737; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.8737; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.8737; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.88409955831
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 1.8840995583126077, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.88)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: left, reward: 2.00090737986
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 29, 't': 1, 'action': 'left', 'reward': 2.000907379863894, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.00)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: -4.89059134202
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': None, 'reward': -4.890591342020544, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.89)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: left, reward: -39.3200969164
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 27, 't': 3, 'action': 'left', 'reward': -39.320096916366005, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.32)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: 1.79916551893
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.7991655189325275, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.80)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: left, reward: 0.301569112358
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 25, 't': 5, 'action': 'left', 'reward': 0.3015691123581562, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove left instead of forward. (rewarded 0.30)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: -5.51872767222
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 24, 't': 6, 'action': None, 'reward': -5.5187276722229885, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.52)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: forward, reward: -40.8854625048
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': -40.88546250482439, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.89)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 1.01174430695
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 1.0117443069458856, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.01)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 1.74614378908
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 1.7461437890764515, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 1.75)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: -4.92522889716
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': -4.925228897161796, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.93)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: right, reward: 0.169744981616
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 0.16974498161602314, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.17)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: 1.94238622374
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.942386223739556, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.94)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: right, reward: 1.52124605252
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 1.5212460525164182, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.52)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: left, reward: 0.61449564432
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 0.6144956443196032, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.61)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: left, reward: -9.97202589981
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 15, 'action': 'left', 'reward': -9.97202589981263, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.97)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: left, reward: -9.85117008892
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': -9.851170088924285, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.85)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: -4.53934485715
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 13, 't': 17, 'action': None, 'reward': -4.539344857152859, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.54)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: forward, reward: -0.127475760287
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 12, 't': 18, 'action': 'forward', 'reward': -0.12747576028650331, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove forward instead of right. (rewarded -0.13)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: right, reward: 0.923477630375
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 11, 't': 19, 'action': 'right', 'reward': 0.9234776303745232, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.92)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: None, reward: 1.18456466756
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.1845646675559582, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.18)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: left, reward: 0.989728829124
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 9, 't': 21, 'action': 'left', 'reward': 0.989728829123631, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.99)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 1.43171787168
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 22, 'action': None, 'reward': 1.4317178716833163, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.43)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: right, reward: 0.0715713288904
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 0.0715713288904295, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.07)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: -4.11665055964
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 24, 'action': None, 'reward': -4.116650559635632, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.12)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 2.07257351559
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 5, 't': 25, 'action': None, 'reward': 2.072573515588706, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.07)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 1.19516595597
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 26, 'action': None, 'reward': 1.1951659559698624, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.20)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: left, reward: -39.4195952412
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 27, 'action': 'left', 'reward': -39.41959524122444, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.42)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: right, reward: -0.551350940908
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 2, 't': 28, 'action': 'right', 'reward': -0.551350940908134, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent drove right instead of left. (rewarded -0.55)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: right, reward: 0.170671841824
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 1, 't': 29, 'action': 'right', 'reward': 0.17067184182382134, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 0.17)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 10
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (7, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.8607; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: None, reward: 2.4505690928
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.4505690927997987, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.45)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 0.4187487739
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.4187487739000507, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 0.42)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: left, reward: -9.36600503869
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': -9.366005038687566, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.37)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: left, reward: -10.0215783977
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -10.0215783976595, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.02)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 1.24309397843
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.2430939784294868, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 1.24)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: forward, reward: -40.3173619605
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': -40.317361960484575, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.32)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: left, reward: -40.4577882963
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'right', 'left'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': -40.457788296278444, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.46)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 0.0371417055465
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': None, 'reward': 0.03714170554650109, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.04)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: forward, reward: -10.0136456329
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': -10.013645632851608, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.01)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: left, reward: 1.68643184028
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.6864318402829874, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 1.69)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: left, reward: -10.0721306828
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': -10.072130682762495, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.07)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: 2.24515442913
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 2.2451544291263907, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.25)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: -9.4406251862
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -9.440625186203729, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -9.44)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 0.517796738123
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.517796738122854, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.52)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: right, reward: 0.37759315487
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 0.37759315487008227, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.38)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: None, reward: 1.38230042085
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.3823004208473337, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.38)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: forward, reward: -0.249731955543
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': -0.24973195554320937, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove forward instead of left. (rewarded -0.25)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: -5.98936405251
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 3, 't': 17, 'action': None, 'reward': -5.989364052512814, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.99)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: right, reward: 0.287966124301
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 0.28796612430141066, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 0.29)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: -4.86603891925
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 1, 't': 19, 'action': None, 'reward': -4.86603891925418, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.87)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 11
\-------------------------

Environment.reset(): Trial set up with start = (7, 7), destination = (3, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.8479; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: left, reward: -39.1869722154
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 30, 't': 0, 'action': 'left', 'reward': -39.18697221535877, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.19)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: left, reward: -10.8241935582
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 29, 't': 1, 'action': 'left', 'reward': -10.824193558201495, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -10.82)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: right, reward: 1.35014329721
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.3501432972129028, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.35)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: forward, reward: 1.1136724386
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 27, 't': 3, 'action': 'forward', 'reward': 1.113672438602677, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove forward instead of left. (rewarded 1.11)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: left, reward: 0.987991765515
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 26, 't': 4, 'action': 'left', 'reward': 0.9879917655150083, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 0.99)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: right, reward: 0.905594765917
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.905594765916825, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.91)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: forward, reward: -9.2930066649
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': -9.29300666490221, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -9.29)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.1323207877
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.1323207877031627, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.13)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: left, reward: -39.9659449716
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 8, 'action': 'left', 'reward': -39.965944971594844, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.97)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: left, reward: -40.7592324152
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 21, 't': 9, 'action': 'left', 'reward': -40.75923241520126, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.76)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: forward, reward: -39.5052625324
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': -39.50526253239545, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.51)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: forward, reward: -0.0581099086657
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': -0.05810990866567367, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded -0.06)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: left, reward: -9.25811054948
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 12, 'action': 'left', 'reward': -9.258110549475324, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.26)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: forward, reward: -10.8433324258
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': -10.843332425818405, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.84)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: right, reward: 0.498202099703
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 0.4982020997028045, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.50)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: forward, reward: -39.0016470708
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 15, 't': 15, 'action': 'forward', 'reward': -39.00164707084863, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.00)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: right, reward: 2.54598693436
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 14, 't': 16, 'action': 'right', 'reward': 2.5459869343585684, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 2.55)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: forward, reward: 0.613392233317
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 0.6133922333169601, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent drove forward instead of right. (rewarded 0.61)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: left, reward: 0.352204408983
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 18, 'action': 'left', 'reward': 0.3522044089829828, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.35)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: left, reward: 0.826122270906
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 11, 't': 19, 'action': 'left', 'reward': 0.8261222709061485, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.83)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: -5.6139129938
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 10, 't': 20, 'action': None, 'reward': -5.61391299380086, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -5.61)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: -0.434719581726
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 9, 't': 21, 'action': None, 'reward': -0.43471958172562364, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded -0.43)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: left, reward: -9.56069044321
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 8, 't': 22, 'action': 'left', 'reward': -9.560690443212467, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.56)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: forward, reward: -9.48339963784
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 7, 't': 23, 'action': 'forward', 'reward': -9.483399637843803, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.48)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: 1.07258106246
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 6, 't': 24, 'action': None, 'reward': 1.0725810624602483, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.07)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: forward, reward: -40.287359105
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 5, 't': 25, 'action': 'forward', 'reward': -40.287359105035385, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.29)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: -5.90331119857
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 4, 't': 26, 'action': None, 'reward': -5.903311198568238, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.90)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: left, reward: -20.1865787648
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 3, 't': 27, 'action': 'left', 'reward': -20.186578764839354, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.19)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: right, reward: 1.25485663055
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 2, 't': 28, 'action': 'right', 'reward': 1.2548566305462956, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.25)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: left, reward: 0.449605878506
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 1, 't': 29, 'action': 'left', 'reward': 0.44960587850583966, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 0.45)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 12
\-------------------------

Environment.reset(): Trial set up with start = (1, 7), destination = (2, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.8353; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.8353; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.8353; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.8353; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: -5.60322013218
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': -5.603220132180348, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -5.60)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: left, reward: 2.20684032852
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 2.2068403285176377, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.21)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: 1.44776211638
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.4477621163815875, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.45)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 1.41221191659
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.412211916587333, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.41)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: -9.47364441407
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': -9.473644414071764, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.47)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 1.8322532451
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.8322532451020848, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 1.83)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: 0.91496706361
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.9149670636100538, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent drove right instead of left. (rewarded 0.91)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 1.86395331542
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.8639533154171468, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.86)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 0.388365157557
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.3883651575568122, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.39)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: left, reward: 2.31121262212
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.3112126221169698, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.31)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: forward, reward: -10.8864473671
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': -10.886447367138192, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -10.89)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: right, reward: 1.48111880753
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.4811188075290518, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.48)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: -0.0305009212526
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': -0.030500921252604396, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove right instead of left. (rewarded -0.03)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.6082729624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.6082729623959373, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.61)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: -10.2260977788
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': -10.226097778758737, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.23)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: forward, reward: -10.8014572819
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -10.801457281909052, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.80)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 2.40179837001
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': None, 'reward': 2.4017983700084082, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.40)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: -0.195357328985
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': -0.1953573289854632, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded -0.20)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: -4.37755319076
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'right', 'left'), 'deadline': 2, 't': 18, 'action': None, 'reward': -4.377553190759088, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.38)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: 1.10609977771
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 1.1060997777142711, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.11)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 13
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (8, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.8228; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: right, reward: 0.959188102418
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 0.9591881024177256, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 0.96)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 0.86884042772
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 0.8688404277197146, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.87)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 0.00180823103178
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 0.0018082310317826256, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.00)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: right, reward: 2.88690352806
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 2.8869035280579345, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.89)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: -4.74483050308
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 21, 't': 4, 'action': None, 'reward': -4.744830503077819, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.74)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: left, reward: 0.593014169224
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 0.5930141692242284, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded 0.59)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: left, reward: -10.4418780654
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': -10.441878065424191, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.44)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: 1.40099233698
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.4009923369759587, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.40)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: right, reward: 0.747574590187
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 0.7475745901872058, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.75)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: right, reward: -0.0938186412985
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': -0.09381864129849182, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded -0.09)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: right, reward: 1.83144483235
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.8314448323479662, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.83)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: right, reward: 1.33934700275
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.3393470027464873, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 1.34)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: forward, reward: 1.37304419365
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 1.3730441936504545, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.37)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 1.84164766498
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.8416476649801365, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.84)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: right, reward: 0.226406334366
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 0.22640633436565338, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.23)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: forward, reward: 0.780100513313
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 0.780100513312747, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove forward instead of left. (rewarded 0.78)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: left, reward: -40.386925908
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 9, 't': 16, 'action': 'left', 'reward': -40.38692590796786, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.39)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: forward, reward: -10.2884360845
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 17, 'action': 'forward', 'reward': -10.28843608447646, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.29)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 2.5063239706
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 7, 't': 18, 'action': None, 'reward': 2.5063239706010965, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.51)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 1.59687964833
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 19, 'action': None, 'reward': 1.596879648328932, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.60)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: right, reward: -0.0279630845716
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 5, 't': 20, 'action': 'right', 'reward': -0.027963084571599683, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent drove right instead of left. (rewarded -0.03)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: left, reward: 1.3286094439
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 4, 't': 21, 'action': 'left', 'reward': 1.3286094439012093, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded 1.33)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: left, reward: -19.5527812171
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 3, 't': 22, 'action': 'left', 'reward': -19.552781217144794, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.55)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: None, reward: -5.05907568015
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 2, 't': 23, 'action': None, 'reward': -5.059075680152803, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -5.06)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: None, reward: -5.80665696446
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 1, 't': 24, 'action': None, 'reward': -5.806656964458544, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.81)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 14
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (1, 5), deadline = 30
Simulating trial. . . 
epsilon = 0.8106; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: forward, reward: 1.06715871343
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': 1.0671587134348126, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent followed the waypoint forward. (rewarded 1.07)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: right, reward: 1.02230487003
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.0223048700267836, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.02)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 1.72312744486
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.7231274448606653, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.72)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 2.01923260695
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 2.0192326069476305, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.02)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: right, reward: 1.6687360085
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 1.6687360085023268, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.67)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: -4.13956085366
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 25, 't': 5, 'action': None, 'reward': -4.13956085366128, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.14)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: right, reward: 1.0300892404
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.0300892403969226, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent drove right instead of left. (rewarded 1.03)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: right, reward: 2.6939752571
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 2.6939752570978452, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.69)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: left, reward: -0.0166521559067
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 22, 't': 8, 'action': 'left', 'reward': -0.01665215590665714, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded -0.02)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: right, reward: 2.4835877263
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 2.483587726301165, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.48)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 2.14578341805
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': 2.1457834180540916, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.15)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: -5.59324034824
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': -5.593240348244603, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.59)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: forward, reward: 0.920806724328
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 18, 't': 12, 'action': 'forward', 'reward': 0.9208067243281923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 0.92)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: left, reward: 1.99238457659
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 1.9923845765909602, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.99)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: 1.64218158706
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 1.6421815870599494, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove left instead of forward. (rewarded 1.64)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 2.58439331564
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 15, 't': 15, 'action': 'right', 'reward': 2.5843933156369925, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.58)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 1.36863298391
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.3686329839059896, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.37)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: -4.11095052744
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 13, 't': 17, 'action': None, 'reward': -4.110950527440353, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.11)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: right, reward: 2.13744376189
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 2.1374437618912063, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 2.14)
37% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 15
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (3, 2), deadline = 30
Simulating trial. . . 
epsilon = 0.7985; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: -5.41690814099
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 30, 't': 0, 'action': None, 'reward': -5.416908140987294, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.42)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: right, reward: 1.9851081349
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.9851081349014863, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 1.99)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: forward, reward: 1.09300935433
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': 1.0930093543280082, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.09)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 2.94860323982
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 2.9486032398191977, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.95)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: forward, reward: -40.0445944929
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': -40.044594492898774, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.04)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: forward, reward: 2.08910423927
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 2.0891042392700756, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.09)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: -5.28545992744
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 24, 't': 6, 'action': None, 'reward': -5.28545992744181, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.29)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: right, reward: 2.788593869
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 2.788593869003492, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 2.79)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: right, reward: 0.622110074394
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 0.6221100743937703, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 0.62)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: 2.79658210896
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'left', 'reward': 2.796582108964196, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.80)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: forward, reward: -10.3815859811
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': -10.38158598114923, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.38)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: right, reward: 1.51283298094
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 1.512832980943887, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove right instead of left. (rewarded 1.51)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 0.952570134466
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 0.9525701344661816, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 0.95)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 1.26869279646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 13, 'action': None, 'reward': 1.2686927964641395, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.27)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 1.50681300142
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 16, 't': 14, 'action': None, 'reward': 1.5068130014223429, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.51)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 1.16311290385
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.1631129038522707, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.16)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: left, reward: -10.4781567251
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': -10.478156725117124, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.48)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: -4.20228408206
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 17, 'action': None, 'reward': -4.202284082055418, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.20)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 1.77261770467
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 1.772617704665652, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 1.77)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 1.6856464136
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 11, 't': 19, 'action': None, 'reward': 1.6856464136023455, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.69)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 1.60946018699
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.6094601869912104, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.61)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 1.72809750001
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 21, 'action': 'forward', 'reward': 1.7280975000134398, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.73)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: right, reward: 0.832019193412
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 8, 't': 22, 'action': 'right', 'reward': 0.8320191934118581, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 0.83)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: forward, reward: 1.78252638378
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 23, 'action': 'forward', 'reward': 1.7825263837766323, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.78)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 16
\-------------------------

Environment.reset(): Trial set up with start = (2, 5), destination = (6, 2), deadline = 35
Simulating trial. . . 
epsilon = 0.7866; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.7866; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.7866; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: forward, reward: 0.265623111874
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 35, 't': 0, 'action': 'forward', 'reward': 0.26562311187428866, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded 0.27)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: left, reward: 1.08938304068
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 34, 't': 1, 'action': 'left', 'reward': 1.089383040682285, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.09)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: right, reward: 1.80341645833
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 33, 't': 2, 'action': 'right', 'reward': 1.803416458325854, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.80)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: left, reward: 0.711257635233
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 32, 't': 3, 'action': 'left', 'reward': 0.711257635233453, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove left instead of forward. (rewarded 0.71)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: right, reward: -19.8142957974
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 31, 't': 4, 'action': 'right', 'reward': -19.814295797354067, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.81)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: forward, reward: -9.39719719606
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 30, 't': 5, 'action': 'forward', 'reward': -9.397197196064266, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.40)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: forward, reward: -9.71845343193
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 29, 't': 6, 'action': 'forward', 'reward': -9.718453431934904, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -9.72)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: left, reward: 1.83946027302
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 28, 't': 7, 'action': 'left', 'reward': 1.8394602730162015, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent drove left instead of right. (rewarded 1.84)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 0.777116223978
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 27, 't': 8, 'action': None, 'reward': 0.7771162239776482, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 0.78)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.78001956388
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 26, 't': 9, 'action': 'right', 'reward': 1.7800195638817282, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.78)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 2.14826710558
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 25, 't': 10, 'action': 'right', 'reward': 2.148267105576178, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 2.15)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: 0.737235680363
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 24, 't': 11, 'action': 'right', 'reward': 0.7372356803625856, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.74)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: right, reward: 0.857137357075
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 12, 'action': 'right', 'reward': 0.8571373570746005, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 0.86)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.85345740491
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 22, 't': 13, 'action': 'right', 'reward': 1.8534574049148436, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.85)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 2.78997163101
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 21, 't': 14, 'action': 'right', 'reward': 2.789971631013291, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.79)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: -4.77672070117
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 20, 't': 15, 'action': None, 'reward': -4.776720701173165, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.78)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: left, reward: 0.79189256163
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 19, 't': 16, 'action': 'left', 'reward': 0.7918925616295324, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.79)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: right, reward: 1.98222433982
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 18, 't': 17, 'action': 'right', 'reward': 1.9822243398205368, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.98)
49% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: forward, reward: 0.771839492754
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 17, 't': 18, 'action': 'forward', 'reward': 0.771839492753734, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent followed the waypoint forward. (rewarded 0.77)
46% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 1.21320945031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 16, 't': 19, 'action': 'right', 'reward': 1.2132094503057451, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.21)
43% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 17
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (6, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.7749; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: left, reward: 2.91646139049
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.916461390485131, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.92)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 1.99454171565
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.9945417156461573, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.99)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 2.39036963628
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.3903696362757074, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.39)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 1.35613082182
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.356130821820632, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.36)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 2.27558072025
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.275580720248972, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.28)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: left, reward: 1.89873336312
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.8987333631214114, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.90)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: left, reward: 0.16166817963
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 0.16166817963009072, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.16)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 2.5311605881
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 2.531160588103356, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.53)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: right, reward: 1.56930981073
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.5693098107335495, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent followed the waypoint right. (rewarded 1.57)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: left, reward: -20.0112430742
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': -20.011243074156347, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.01)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: forward, reward: -39.3515946178
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': -39.35159461781956, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.35)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: forward, reward: -9.41056063709
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': -9.410560637086421, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -9.41)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 1.2489125891
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.248912589098624, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.25)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 0.769738689096
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 7, 't': 13, 'action': None, 'reward': 0.7697386890962192, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.77)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: left, reward: -9.8180240413
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': -9.818024041295876, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -9.82)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 0.539142601083
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 0.5391426010829539, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.54)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: forward, reward: -39.6097281905
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': -39.60972819051703, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.61)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 0.983230512836
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 0.9832305128363623, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.98)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: left, reward: 1.00908139789
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 2, 't': 18, 'action': 'left', 'reward': 1.0090813978912596, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 1.01)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: left, reward: -10.9041279968
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -10.904127996786272, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -10.90)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 18
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (3, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.7634; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 2.95993017127
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.95993017127192, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.96)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 1.67153530734
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.6715353073351193, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.67)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 1.01117759209
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.011177592090217, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.01)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: left, reward: -10.0711557903
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -10.071155790346669, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.07)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: left, reward: 1.89632975184
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.8963297518370177, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.90)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: forward, reward: -10.9659319577
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': -10.965931957686147, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.97)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: left, reward: 0.0697391741581
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 0.0697391741580593, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded 0.07)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: forward, reward: 0.601172154215
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 0.6011721542149087, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 0.60)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: forward, reward: 1.02021135755
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 1.020211357548369, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove forward instead of right. (rewarded 1.02)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: -4.82079719006
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': -4.82079719006007, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.82)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: right, reward: -0.223189529812
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': -0.22318952981172446, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove right instead of forward. (rewarded -0.22)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 2.49469410464
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.4946941046379862, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.49)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: forward, reward: -10.0919176846
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -10.09191768462413, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.09)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 1.73024327933
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.7302432793348268, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.73)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 1.38802969114
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.3880296911357057, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.39)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: forward, reward: -10.803455036
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -10.803455036008552, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.80)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: -5.86226734603
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': None, 'reward': -5.86226734602864, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.86)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: -4.56780149644
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': None, 'reward': -4.567801496442989, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.57)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: 0.823903476827
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 2, 't': 18, 'action': 'left', 'reward': 0.8239034768269728, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.82)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: left, reward: -0.688467346095
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -0.6884673460949121, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, 'left')
Agent drove left instead of forward. (rewarded -0.69)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 19
\-------------------------

Environment.reset(): Trial set up with start = (3, 7), destination = (7, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.7520; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.7520; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: left, reward: -9.87839304225
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 30, 't': 0, 'action': 'left', 'reward': -9.878393042254535, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent attempted driving left through a red light. (rewarded -9.88)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: None, reward: 1.17348381676
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 29, 't': 1, 'action': None, 'reward': 1.1734838167574853, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.17)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: right, reward: 2.30201679518
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 2.3020167951798896, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.30)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: right, reward: 1.90877055624
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 1.9087705562444244, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.91)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 0.275804225557
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 0.275804225557157, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 0.28)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: forward, reward: -10.611809379
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': -10.611809378972799, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.61)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: right, reward: -0.0300177397029
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': -0.03001773970286503, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded -0.03)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: right, reward: 2.20756813504
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 2.207568135043055, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.21)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: right, reward: 1.77513758616
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 1.7751375861630114, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.78)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: -10.1128504979
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': -10.112850497857078, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.11)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: 0.913243429207
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 20, 't': 10, 'action': None, 'reward': 0.9132434292074647, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.91)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: forward, reward: 1.49794077984
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': 1.4979407798411701, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.50)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: left, reward: 1.50196707797
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 12, 'action': 'left', 'reward': 1.5019670779736098, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.50)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: left, reward: 0.673356781096
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 0.6733567810961205, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.67)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: -4.91134413957
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 16, 't': 14, 'action': None, 'reward': -4.9113441395668245, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.91)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: left, reward: -9.71485753163
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 15, 'action': 'left', 'reward': -9.714857531628272, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.71)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: left, reward: -10.0022489715
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': -10.002248971522098, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.00)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: -5.41132911989
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 17, 'action': None, 'reward': -5.411329119891089, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.41)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: forward, reward: 0.951213712352
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 12, 't': 18, 'action': 'forward', 'reward': 0.9512137123517928, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 0.95)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: left, reward: -0.151819041859
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 11, 't': 19, 'action': 'left', 'reward': -0.1518190418586386, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded -0.15)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 2.37502887292
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 20, 'action': None, 'reward': 2.3750288729171976, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.38)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: left, reward: 0.837851862263
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'left', 'reward': 0.837851862262583, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.84)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: -0.267805143138
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 22, 'action': 'right', 'reward': -0.2678051431383004, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded -0.27)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: forward, reward: 0.00355044209108
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 7, 't': 23, 'action': 'forward', 'reward': 0.0035504420910815737, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove forward instead of left. (rewarded 0.00)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: left, reward: 1.80069171617
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 24, 'action': 'left', 'reward': 1.8006917161740326, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.80)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 0.832937923581
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 0.8329379235807428, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.83)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: left, reward: 0.564424166817
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 26, 'action': 'left', 'reward': 0.5644241668170664, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.56)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: right, reward: 0.423732515687
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 3, 't': 27, 'action': 'right', 'reward': 0.4237325156870735, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.42)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: right, reward: -0.652544872788
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 2, 't': 28, 'action': 'right', 'reward': -0.6525448727878681, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded -0.65)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: left, reward: -19.096783715
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 1, 't': 29, 'action': 'left', 'reward': -19.096783715027286, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', 'right', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.10)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 20
\-------------------------

Environment.reset(): Trial set up with start = (8, 2), destination = (5, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.7408; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 1.74055508842
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.7405550884152938, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.74)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 2.1389742495
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.138974249502878, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 2.14127768268
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.1412776826841435, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: left, reward: -9.6133543346
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -9.61335433460112, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.61)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: left, reward: -10.0890839444
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': -10.08908394443906, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.09)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 1.79137020636
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.791370206358356, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.79)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: None, reward: -5.56251119688
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': -5.5625111968799965, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.56)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: 1.16792215278
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.1679221527841808, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.17)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: left, reward: 1.78099863191
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 1.7809986319147397, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.78)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 1.65770621311
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.657706213112312, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.66)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: right, reward: -0.126954590654
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': -0.12695459065397074, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded -0.13)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 2.56803304874
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.5680330487405194, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.57)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: forward, reward: -10.0279699639
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -10.027969963877084, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.03)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: forward, reward: 0.376572190657
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 0.3765721906565437, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove forward instead of left. (rewarded 0.38)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: -5.2179011303
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': -5.217901130302756, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.22)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: 1.94338685194
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.943386851937519, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.94)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: forward, reward: 2.36506453064
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 2.3650645306395557, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.37)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: left, reward: -39.4574961438
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 3, 't': 17, 'action': 'left', 'reward': -39.45749614384313, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.46)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 5), heading: (0, -1), action: right, reward: -0.069803480027
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 2, 't': 18, 'action': 'right', 'reward': -0.06980348002702619, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded -0.07)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 5), heading: (0, -1), action: left, reward: -9.06537969281
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -9.0653796928104, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.07)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 21
\-------------------------

Environment.reset(): Trial set up with start = (6, 4), destination = (2, 6), deadline = 30
Simulating trial. . . 
epsilon = 0.7298; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: forward, reward: 2.06339203546
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': 2.063392035460115, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.06)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: 1.78057657187
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 29, 't': 1, 'action': 'left', 'reward': 1.7805765718652822, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.78)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: forward, reward: -39.004826008
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'forward', 'forward'), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': -39.004826008035316, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.00)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: -10.3107579076
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 27, 't': 3, 'action': 'left', 'reward': -10.310757907614425, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -10.31)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: None, reward: 0.113945141977
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 0.11394514197714523, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 0.11)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: -20.2361451651
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 25, 't': 5, 'action': 'left', 'reward': -20.236145165087585, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.24)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: -20.9325486051
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 24, 't': 6, 'action': 'left', 'reward': -20.93254860514032, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.93)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: left, reward: 0.151676634087
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 23, 't': 7, 'action': 'left', 'reward': 0.15167663408704912, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.15)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 1.55042329259
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 1.5504232925929344, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.55)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: -39.4251426588
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 21, 't': 9, 'action': 'left', 'reward': -39.425142658839306, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.43)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: forward, reward: 0.844646665055
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 0.8446466650546187, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded 0.84)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: -4.66355570935
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': -4.663555709354386, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.66)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 1.18529527887
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 1.1852952788673305, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.19)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: -10.7669192553
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': -10.766919255278994, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.77)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: left, reward: -9.58645184272
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 14, 'action': 'left', 'reward': -9.58645184271808, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.59)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.25223758039
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 15, 't': 15, 'action': None, 'reward': 2.2522375803932313, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.25)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: -5.78869904678
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': -5.788699046784144, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.79)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: left, reward: -0.236160383618
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 13, 't': 17, 'action': 'left', 'reward': -0.23616038361843117, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded -0.24)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: None, reward: 0.278649515263
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 18, 'action': None, 'reward': 0.2786495152625921, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.28)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: left, reward: 0.443108746416
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 11, 't': 19, 'action': 'left', 'reward': 0.44310874641591436, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.44)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 1.0527512127
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 10, 't': 20, 'action': 'forward', 'reward': 1.0527512127004606, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 1.05)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: None, reward: -4.88729994906
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 9, 't': 21, 'action': None, 'reward': -4.887299949055348, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.89)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: None, reward: 0.804629791461
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 8, 't': 22, 'action': None, 'reward': 0.804629791460727, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 0.80)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: right, reward: 1.07404609547
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.0740460954687636, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent drove right instead of forward. (rewarded 1.07)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: right, reward: 0.985477776717
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 6, 't': 24, 'action': 'right', 'reward': 0.9854777767172072, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove right instead of left. (rewarded 0.99)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: -4.89348449533
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 5, 't': 25, 'action': None, 'reward': -4.893484495330963, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.89)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 2.23922304416
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 4, 't': 26, 'action': None, 'reward': 2.239223044160287, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.24)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: left, reward: -9.38770219609
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 3, 't': 27, 'action': 'left', 'reward': -9.387702196086273, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent attempted driving left through a red light. (rewarded -9.39)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: left, reward: -9.41816030095
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 2, 't': 28, 'action': 'left', 'reward': -9.418160300950248, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent attempted driving left through a red light. (rewarded -9.42)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: -10.6783181265
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 1, 't': 29, 'action': 'forward', 'reward': -10.678318126482283, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.68)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 22
\-------------------------

Environment.reset(): Trial set up with start = (6, 3), destination = (3, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.7189; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: left, reward: 0.281835641308
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 0.28183564130813155, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.28)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: left, reward: 1.00905694453
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.0090569445293056, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.01)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: 1.08904720935
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.0890472093486205, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.09)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: left, reward: 0.757315800198
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 0.7573158001976877, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.76)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: forward, reward: 2.20518295112
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.205182951122538, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.21)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: -4.40392382533
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': -4.403923825325524, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.40)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: forward, reward: 1.53451329438
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.5345132943760793, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.53)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 1.46470338945
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.4647033894465211, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.46)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 0.90402018088
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 0.9040201808795809, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.90)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 0.568864244799
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 0.5688642447985435, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.57)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: forward, reward: 1.38039402568
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 1.3803940256768943, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.38)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: forward, reward: 0.237834425884
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 0.23783442588402748, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove forward instead of left. (rewarded 0.24)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: left, reward: 0.919857395693
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 8, 't': 12, 'action': 'left', 'reward': 0.9198573956926654, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 0.92)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: 1.42788094362
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.4278809436234972, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.43)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: -9.81303027067
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': -9.8130302706684, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.81)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 1.41504707404
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': 1.4150470740377181, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 1.42)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 0.413953046678
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.4139530466778938, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.41)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: 2.05780361032
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 2.057803610320751, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.06)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: 0.11776382119
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 2, 't': 18, 'action': 'left', 'reward': 0.11776382119004136, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.12)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: left, reward: -0.522655293064
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -0.5226552930641241, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded -0.52)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 23
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (3, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.7082; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: left, reward: -20.0928748149
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': -20.09287481494029, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.09)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: left, reward: 2.63716345831
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 2.637163458313367, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.64)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 1.15841535269
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.1584153526902, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.16)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 1.69499188711
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.694991887106362, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.69)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 1.54332405564
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.5433240556354555, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove right instead of left. (rewarded 1.54)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 1.08660115185
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.0866011518534964, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.09)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 0.32233059508
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.32233059508003836, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.32)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: forward, reward: -40.1684893218
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': -40.168489321810284, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.17)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 2.67751694478
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.677516944777962, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.68)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: -5.64427916246
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': -5.644279162464817, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.64)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: forward, reward: 0.708611603827
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 0.7086116038268949, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 0.71)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: 2.11615730837
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.1161573083656906, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.12)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: 1.31402898912
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.3140289891171717, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.31)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: right, reward: -0.239322024987
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 7, 't': 13, 'action': 'right', 'reward': -0.23932202498703725, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove right instead of left. (rewarded -0.24)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: None, reward: 0.865730676633
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 0.8657306766333823, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.87)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: -0.247291185905
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': -0.24729118590512456, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded -0.25)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: -4.9163701777
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 4, 't': 16, 'action': None, 'reward': -4.916370177698129, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.92)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: -20.3091389207
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 3, 't': 17, 'action': 'right', 'reward': -20.309138920658235, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.31)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: forward, reward: -9.03736655452
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 2, 't': 18, 'action': 'forward', 'reward': -9.03736655451935, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.04)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: right, reward: 0.2640230745
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 0.26402307449965656, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.26)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 24
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (6, 2), deadline = 30
Simulating trial. . . 
epsilon = 0.6977; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: right, reward: 0.828342960201
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 0.8283429602005257, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent drove right instead of forward. (rewarded 0.83)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: right, reward: 1.55457158329
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.5545715832920677, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.55)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: -4.68780871174
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': None, 'reward': -4.687808711743785, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.69)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: right, reward: 0.48979958393
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 0.4897995839298822, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.49)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: left, reward: -19.7646155485
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 26, 't': 4, 'action': 'left', 'reward': -19.764615548519494, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.76)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: None, reward: -4.23345027513
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 25, 't': 5, 'action': None, 'reward': -4.233450275125033, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.23)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: left, reward: 1.30652164194
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 24, 't': 6, 'action': 'left', 'reward': 1.3065216419377297, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.31)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: left, reward: -9.51908037287
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 7, 'action': 'left', 'reward': -9.519080372872752, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.52)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: forward, reward: -10.165823441
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': 'forward', 'reward': -10.165823440964779, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.17)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: None, reward: -4.31380163013
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 21, 't': 9, 'action': None, 'reward': -4.3138016301310484, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.31)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: left, reward: 1.65815757743
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': 1.6581575774325745, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.66)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 0.784583182332
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'forward'), 'deadline': 19, 't': 11, 'action': None, 'reward': 0.784583182331973, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 0.78)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: forward, reward: -9.64076963472
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 18, 't': 12, 'action': 'forward', 'reward': -9.64076963472396, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent attempted driving forward through a red light. (rewarded -9.64)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: right, reward: 1.98594183753
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 1.9859418375298705, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.99)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: left, reward: -9.18181232398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 14, 'action': 'left', 'reward': -9.181812323981053, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.18)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: right, reward: -20.8893477789
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 15, 't': 15, 'action': 'right', 'reward': -20.889347778912587, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.89)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: 0.890684080506
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'forward', 'reward': 0.8906840805064888, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.89)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: right, reward: 1.7247581434
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 1.7247581434032149, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.72)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: forward, reward: -10.1552683547
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 18, 'action': 'forward', 'reward': -10.155268354735576, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.16)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: forward, reward: 0.745198536514
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': 0.7451985365139686, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.75)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: right, reward: 1.19213796573
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 10, 't': 20, 'action': 'right', 'reward': 1.1921379657272198, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.19)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: left, reward: -40.2175428044
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 9, 't': 21, 'action': 'left', 'reward': -40.21754280438396, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.22)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: left, reward: -9.67378409583
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 8, 't': 22, 'action': 'left', 'reward': -9.673784095826976, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -9.67)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 0.851775548773
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 7, 't': 23, 'action': None, 'reward': 0.8517755487734198, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.85)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 0.609341589884
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 24, 'action': None, 'reward': 0.6093415898835333, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.61)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: -0.0464067041085
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 5, 't': 25, 'action': 'right', 'reward': -0.04640670410845016, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded -0.05)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: left, reward: 0.492176956469
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 4, 't': 26, 'action': 'left', 'reward': 0.4921769564687857, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded 0.49)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 1.32246066577
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 27, 'action': None, 'reward': 1.3224606657726548, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.32)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 1.71951894097
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'forward'), 'deadline': 2, 't': 28, 'action': None, 'reward': 1.7195189409675724, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.72)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: left, reward: 1.74268398607
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 1, 't': 29, 'action': 'left', 'reward': 1.7426839860730003, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.74)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 25
\-------------------------

Environment.reset(): Trial set up with start = (7, 4), destination = (1, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.6873; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 1.115216242
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.1152162420002627, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.12)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: -9.83948646284
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', 'right'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': -9.839486462844514, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'right')
Agent attempted driving left through a red light. (rewarded -9.84)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: -10.7814392928
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': -10.781439292768711, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -10.78)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: -19.0379462128
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -19.037946212791457, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.04)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: forward, reward: 1.68361181323
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.6836118132302702, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 1.68)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: 2.04784579874
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.047845798739601, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.05)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: -9.45977314793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': -9.459773147926855, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -9.46)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: -9.81720030981
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': -9.817200309811213, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent attempted driving left through a red light. (rewarded -9.82)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: -39.0297528553
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 12, 't': 8, 'action': 'left', 'reward': -39.02975285531215, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.03)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.32186118448
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.3218611844782302, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.32)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: right, reward: 1.20026087601
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.2002608760130054, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.20)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: right, reward: -0.0107112225
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': -0.010711222499968143, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent drove right instead of left. (rewarded -0.01)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: -4.71482011718
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 8, 't': 12, 'action': None, 'reward': -4.714820117178322, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.71)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: right, reward: 1.00496377739
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 1.0049637773947673, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent drove right instead of left. (rewarded 1.00)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: -4.03411202969
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 6, 't': 14, 'action': None, 'reward': -4.034112029685737, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.03)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: left, reward: 0.841155930167
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 0.8411559301667109, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.84)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: left, reward: -40.2988166764
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': -40.29881667638122, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.30)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 0.835376278447
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 0.8353762784472885, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.84)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.25985247167
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.2598524716668011, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.26)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: left, reward: -10.1514778056
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -10.151477805586476, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.15)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 26
\-------------------------

Environment.reset(): Trial set up with start = (6, 4), destination = (8, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.6771; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: left, reward: 2.22825834595
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.2282583459470073, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.23)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: right, reward: 0.905690205911
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.9056902059114061, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.91)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: left, reward: -9.65475750813
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': -9.654757508129062, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent attempted driving left through a red light. (rewarded -9.65)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: forward, reward: -10.5667120706
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': -10.56671207058175, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.57)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 1.78634283245
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.7863428324533437, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.79)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: right, reward: -0.0673316069674
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': -0.06733160696738127, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded -0.07)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: left, reward: 2.78737557347
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 2.7873755734669943, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.79)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: right, reward: -0.0562370561087
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': 'right', 'reward': -0.05623705610873997, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent drove right instead of left. (rewarded -0.06)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: None, reward: -5.17816272361
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': -5.178162723613872, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.18)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: left, reward: 0.873067235204
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 0.873067235204209, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.87)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: left, reward: 2.16509698188
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.165096981882148, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.17)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.91573942081
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.915739420813914, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.92)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.82582023499
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.8258202349869361, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.83)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 0.713849610733
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.7138496107332556, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.71)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: None, reward: 1.96521160727
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.965211607269037, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.97)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: left, reward: -40.0636390768
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 5, 't': 15, 'action': 'left', 'reward': -40.06363907675701, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.06)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: forward, reward: -0.218557337838
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': -0.21855733783771325, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded -0.22)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: forward, reward: 0.0872976920862
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 0.08729769208624483, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 0.09)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: 0.725918908087
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.7259189080870179, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.73)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: 2.03626984197
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 2.036269841974727, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.04)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 27
\-------------------------

Environment.reset(): Trial set up with start = (1, 3), destination = (7, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.6670; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6670; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6670; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.63156539104
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.6315653910416152, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.63)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 1.20107439551
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.2010743955057057, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.20)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: -9.67654517642
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': -9.676545176421495, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.68)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.88492659388
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.884926593876428, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.88)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: -10.464708565
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': -10.464708565005825, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.46)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 0.783642648085
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 0.7836426480845522, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.78)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: left, reward: 2.72105983223
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 2.7210598322324397, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.72)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 1.69927407296
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.6992740729571958, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.70)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 2.56732918264
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.5673291826374713, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.57)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: right, reward: 1.04922779979
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.0492277997909998, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.05)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: left, reward: -40.2787247789
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': -40.278724778932194, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.28)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 1.07950384511
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.079503845111201, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 1.08)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: right, reward: 1.33322552275
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.3332255227516157, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.33)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 0.713041900036
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 7, 't': 13, 'action': None, 'reward': 0.7130419000359091, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.71)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: left, reward: -9.56055710247
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 6, 't': 14, 'action': 'left', 'reward': -9.560557102470206, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent attempted driving left through a red light. (rewarded -9.56)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: left, reward: -9.52385391885
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': -9.52385391885059, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.52)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: -9.26262732815
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': -9.262627328150728, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.26)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 2.29279815705
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 2.2927981570480394, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.29)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: forward, reward: 1.97342012521
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 2, 't': 18, 'action': 'forward', 'reward': 1.9734201252088328, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.97)
5% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 28
\-------------------------

Environment.reset(): Trial set up with start = (8, 3), destination = (3, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.6570; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6570; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6570; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6570; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6570; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: -4.27216915438
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': -4.2721691543777895, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.27)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: left, reward: 2.90135733069
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 2.9013573306944185, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.90)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.303667694
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.3036676939962928, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.30)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: forward, reward: -9.74032439327
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': -9.740324393267729, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.74)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.01276271467
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.0127627146695954, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.01)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 2.56358649827
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.5635864982721883, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.56)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: -4.20307588189
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 14, 't': 6, 'action': None, 'reward': -4.203075881887624, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -4.20)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: right, reward: 1.49023045073
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.4902304507281967, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.49)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: -4.21663075329
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': -4.216630753290039, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.22)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 1.38931105624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.3893110562370525, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.39)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: right, reward: 1.16866100262
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.168661002621006, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.17)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: right, reward: 1.0277795205
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.0277795205049765, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.03)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: 0.760715836956
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 0.7607158369555518, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 0.76)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 0.585076587714
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.5850765877143705, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.59)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: -4.56602072375
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 6, 't': 14, 'action': None, 'reward': -4.56602072374653, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.57)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: -0.28801601382
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 5, 't': 15, 'action': 'right', 'reward': -0.2880160138196821, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove right instead of left. (rewarded -0.29)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 0.695817637769
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 4, 't': 16, 'action': None, 'reward': 0.6958176377685028, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 0.70)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 1.90860240662
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 1.9086024066178156, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent followed the waypoint right. (rewarded 1.91)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: -0.634321608702
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 2, 't': 18, 'action': None, 'reward': -0.6343216087017576, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded -0.63)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 0.34030535359
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 0.34030535358962655, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', 'forward', 'left')
Agent followed the waypoint right. (rewarded 0.34)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 29
\-------------------------

Environment.reset(): Trial set up with start = (6, 2), destination = (3, 4), deadline = 25
Simulating trial. . . 
epsilon = 0.6473; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6473; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: forward, reward: -10.8633006606
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': -10.863300660560268, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.86)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: -9.55132450295
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': -9.551324502945038, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.55)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: 1.29256252693
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.292562526929603, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.29)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: -9.07554403163
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': -9.075544031631516, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.08)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: left, reward: 2.50664902719
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 2.5066490271878576, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.51)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: forward, reward: 1.8689602635
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 1.8689602635009779, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.87)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: left, reward: -10.6811511882
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': -10.681151188220472, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.68)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: forward, reward: -9.70121094908
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': -9.701210949081249, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.70)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: 2.45600781165
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.4560078116529693, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.46)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: left, reward: 1.79701716151
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 1.7970171615095356, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 1.80)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: left, reward: 0.782997020944
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 0.7829970209442759, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.78)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: 0.481420191147
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'forward'), 'deadline': 14, 't': 11, 'action': None, 'reward': 0.4814201911470958, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 0.48)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: right, reward: 1.5440950443
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 1.5440950443019468, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.54)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: forward, reward: 1.13820197027
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 1.138201970272188, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove forward instead of right. (rewarded 1.14)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: left, reward: -40.9229704695
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 11, 't': 14, 'action': 'left', 'reward': -40.92297046951731, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.92)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: right, reward: 1.1534011827
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 1.1534011827000497, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.15)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: forward, reward: -40.2998905466
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': -40.29989054661113, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.30)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: right, reward: 1.1472562739
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 17, 'action': 'right', 'reward': 1.147256273895283, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.15)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: -39.5685630137
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 7, 't': 18, 'action': 'forward', 'reward': -39.56856301372391, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.57)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: left, reward: -9.71892600675
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 19, 'action': 'left', 'reward': -9.718926006753401, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.72)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: -10.0396368998
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 20, 'action': 'forward', 'reward': -10.039636899766855, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.04)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: left, reward: 1.20671217286
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 21, 'action': 'left', 'reward': 1.2067121728609478, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.21)
12% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 30
\-------------------------

Environment.reset(): Trial set up with start = (4, 6), destination = (8, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.6376; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: 1.68710759588
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.687107595883267, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.69)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 0.66562268723
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.6656226872295384, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 0.67)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 1.14919059056
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.1491905905564206, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.15)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.61298783301
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.6129878330062635, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.61)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 1.38359515625
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.3835951562526354, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 1.38)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 1.99264374889
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.9926437488893673, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.99)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: left, reward: -9.82730764188
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': -9.827307641878757, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.83)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: right, reward: 2.31796689874
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 2.3179668987403304, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.32)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: 1.34565284175
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 1.3456528417538722, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.35)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: -39.9088811199
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'right', 'forward'), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': -39.90888111986948, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.91)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: -10.3538144805
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': -10.35381448050243, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent attempted driving forward through a red light. (rewarded -10.35)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: 0.795184430239
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 0.7951844302389459, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 0.80)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: None, reward: 0.0998358836874
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 0.09983588368742446, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 0.10)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: -19.3580757175
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 7, 't': 13, 'action': 'left', 'reward': -19.358075717461535, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.36)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: -0.0936714826646
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': -0.09367148266456271, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove forward instead of right. (rewarded -0.09)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: forward, reward: -0.510278361367
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -0.510278361366632, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded -0.51)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: -0.427814922946
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 4, 't': 16, 'action': None, 'reward': -0.4278149229458994, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent properly idled at a red light. (rewarded -0.43)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: -4.57540956235
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 3, 't': 17, 'action': None, 'reward': -4.575409562352122, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.58)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 2.13509345162
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 2.1350934516176285, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.14)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.00841578094
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 1, 't': 19, 'action': None, 'reward': 2.0084157809404615, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.01)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 31
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (1, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.6281; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6281; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6281; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6281; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.6281; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: right, reward: 0.399086212758
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 0.39908621275786316, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.40)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: -40.5995470827
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': -40.59954708271274, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.60)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: -9.37745152571
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': -9.377451525706855, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -9.38)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: -9.8771847873
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': -9.877184787295684, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.88)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: -39.2817162717
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': -39.28171627172372, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.28)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: None, reward: 2.52316938465
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.523169384652817, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 2.52)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: left, reward: -20.8221581165
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': -20.822158116496105, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.82)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: right, reward: -0.00244195304263
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': -0.002441953042625178, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded -0.00)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: left, reward: 0.411549964718
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 0.4115499647177526, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove left instead of forward. (rewarded 0.41)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: right, reward: 2.47272345825
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 2.4727234582499396, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.47)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: -10.9157030145
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': -10.915703014527981, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.92)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: 1.32029806432
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.3202980643241942, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 1.32)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: 1.09443390891
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.0944339089132775, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.09)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: forward, reward: 1.59273894161
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.592738941607657, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent drove forward instead of right. (rewarded 1.59)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: left, reward: 0.278588160842
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 6, 't': 14, 'action': 'left', 'reward': 0.2785881608419122, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.28)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: 0.930776391654
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 0.9307763916537803, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.93)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 0.370899413865
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 4, 't': 16, 'action': None, 'reward': 0.37089941386517267, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.37)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 1.01565973744
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.0156597374352674, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.02)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: left, reward: -9.76166073508
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 2, 't': 18, 'action': 'left', 'reward': -9.761660735077548, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.76)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: -4.00053256951
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 1, 't': 19, 'action': None, 'reward': -4.000532569509499, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.00)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 32
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (3, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.6188; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 2.07781773472
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.0778177347205675, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 2.08)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: left, reward: 1.38330032706
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.3833003270550681, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 1.38)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: -5.8314659383
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': -5.831465938297025, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.83)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: right, reward: 1.52730691192
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.5273069119187785, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.53)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: 0.330375813342
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 0.33037581334231814, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove forward instead of right. (rewarded 0.33)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: -40.0231395132
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': -40.0231395131945, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.02)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: left, reward: -9.20041743249
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': -9.200417432493271, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.20)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 0.372480714076
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 13, 't': 7, 'action': None, 'reward': 0.3724807140755406, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.37)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 1.94568188985
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.9456818898508397, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.95)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 1.23699351978
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.2369935197822979, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.24)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 0.975829951443
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 0.9758299514431629, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 0.98)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 1.65295237223
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.6529523722262052, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.65)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: left, reward: -10.1480884029
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 8, 't': 12, 'action': 'left', 'reward': -10.14808840285795, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent attempted driving left through a red light. (rewarded -10.15)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 1.22080458874
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 1.2208045887385401, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.22)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 0.597944995075
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 6, 't': 14, 'action': None, 'reward': 0.5979449950745345, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.60)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: -39.7581826469
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -39.75818264688026, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.76)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 0.851402337734
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.8514023377336224, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.85)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: forward, reward: 1.31862361845
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 1.3186236184483269, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.32)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: 1.36825611762
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.3682561176223822, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.37)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: forward, reward: 1.09120794587
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': 1.0912079458705761, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.09)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 33
\-------------------------

Environment.reset(): Trial set up with start = (8, 7), destination = (4, 5), deadline = 30
Simulating trial. . . 
epsilon = 0.6096; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: -10.4260869758
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': -10.426086975799054, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.43)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 2.67266397253
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 2.6726639725313768, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.67)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: forward, reward: -9.3593481822
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': -9.359348182197106, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.36)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: left, reward: -10.9705151068
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 27, 't': 3, 'action': 'left', 'reward': -10.970515106769563, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.97)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: -4.01018103569
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': -4.010181035689338, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.01)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: right, reward: 1.64128609037
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 1.6412860903726039, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent followed the waypoint right. (rewarded 1.64)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: None, reward: 2.84674442346
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 6, 'action': None, 'reward': 2.8467444234550996, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.85)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: None, reward: 2.88462762401
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 23, 't': 7, 'action': None, 'reward': 2.88462762401344, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.88)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: left, reward: -9.72042189187
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': 'left', 'reward': -9.720421891872343, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.72)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: forward, reward: 1.99573999754
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 1.9957399975423964, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.00)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 0.804844783652
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 20, 't': 10, 'action': 'right', 'reward': 0.8048447836517847, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.80)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: left, reward: 1.2134215193
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'left', 'reward': 1.2134215193039593, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.21)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: forward, reward: 1.79086385048
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 12, 'action': 'forward', 'reward': 1.7908638504821544, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.79)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: forward, reward: -10.2725870025
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': -10.27258700254337, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.27)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: left, reward: -40.3897364463
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': -40.38973644630567, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.39)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: left, reward: -19.0586430069
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 15, 't': 15, 'action': 'left', 'reward': -19.058643006894478, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.06)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: -5.34931405168
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': -5.349314051678457, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.35)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 1.09663385021
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 17, 'action': None, 'reward': 1.0966338502087034, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.10)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 1.04212578488
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 18, 'action': None, 'reward': 1.0421257848849592, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.04)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: forward, reward: 0.984093790753
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': 0.9840937907534478, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.98)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: left, reward: 2.42255328798
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 10, 't': 20, 'action': 'left', 'reward': 2.4225532879756413, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.42)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: forward, reward: 1.04580754291
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 9, 't': 21, 'action': 'forward', 'reward': 1.0458075429149658, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove forward instead of left. (rewarded 1.05)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: left, reward: -9.92337345661
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 22, 'action': 'left', 'reward': -9.9233734566069, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.92)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: forward, reward: -10.4055253174
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 7, 't': 23, 'action': 'forward', 'reward': -10.40552531739623, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.41)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: 1.46136261167
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 6, 't': 24, 'action': None, 'reward': 1.4613626116689296, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.46)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: -5.46799233544
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 25, 'action': None, 'reward': -5.4679923354408775, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.47)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: left, reward: 1.49457109714
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 4, 't': 26, 'action': 'left', 'reward': 1.4945710971442017, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.49)
10% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 34
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (1, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.6005; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: left, reward: -40.7157660364
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 25, 't': 0, 'action': 'left', 'reward': -40.71576603639828, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.72)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: None, reward: 1.80563717674
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.8056371767424975, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.81)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: forward, reward: -9.10597605699
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': -9.105976056988796, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.11)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: left, reward: 1.19356966568
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 1.1935696656794677, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.19)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 2.38625417474
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.386254174737043, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.39)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 1.38706051987
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.3870605198673387, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.39)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: right, reward: 1.80875023503
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 1.8087502350267668, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 1.81)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: left, reward: 1.16013219235
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 1.1601321923501025, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.16)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: right, reward: 0.432508700496
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 0.43250870049590573, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent drove right instead of forward. (rewarded 0.43)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: left, reward: -10.6462731782
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 9, 'action': 'left', 'reward': -10.64627317816888, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -10.65)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: right, reward: 1.1328869799
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.1328869798993062, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.13)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: -4.36163224686
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 11, 'action': None, 'reward': -4.361632246856765, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.36)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: forward, reward: 1.08830981819
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 1.088309818186901, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.09)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 1.28083247626
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.2808324762620418, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.28)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 1.96221903445
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.9622190344492487, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.96)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 2.43229426866
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 10, 't': 15, 'action': None, 'reward': 2.4322942686640285, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.43)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: left, reward: 0.688083559819
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'left', 'reward': 0.6880835598193475, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.69)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 1.77093252062
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 8, 't': 17, 'action': None, 'reward': 1.7709325206177726, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.77)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 2.02111747523
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 7, 't': 18, 'action': None, 'reward': 2.0211174752256547, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.02)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 1.38692645806
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 6, 't': 19, 'action': 'right', 'reward': 1.3869264580635932, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 1.39)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: forward, reward: -10.3237328275
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 20, 'action': 'forward', 'reward': -10.323732827519452, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.32)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: 2.11985626233
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': 2.1198562623277954, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.12)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: left, reward: -40.6672434775
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 3, 't': 22, 'action': 'left', 'reward': -40.667243477533745, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.67)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 0.956038958471
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 2, 't': 23, 'action': None, 'reward': 0.9560389584712776, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.96)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.93245785399
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 24, 'action': None, 'reward': 1.9324578539882844, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.93)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 35
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (3, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.5916; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5916; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5916; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5916; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: right, reward: 2.34614252469
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.346142524685508, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.35)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: left, reward: 0.657657361288
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 0.6576573612875548, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove left instead of forward. (rewarded 0.66)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: right, reward: 2.44131314782
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.4413131478152836, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.44)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: left, reward: -9.63278328041
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -9.632783280405164, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.63)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.35536316666
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.355363166655418, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.36)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: right, reward: 2.44476070878
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 2.4447607087842624, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.44)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: left, reward: -10.8314390995
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': -10.831439099526822, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.83)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: left, reward: 0.716261597708
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 0.7162615977076019, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 0.72)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: left, reward: 0.936931865188
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 0.936931865187873, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent drove left instead of right. (rewarded 0.94)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: left, reward: -40.7999558539
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': -40.79995585393798, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.80)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: right, reward: 1.72897732645
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.728977326447192, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 1.73)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: right, reward: 0.804665487816
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.80466548781578, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 0.80)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: forward, reward: -9.36342398026
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -9.363423980260196, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.36)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: forward, reward: 1.60638589918
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.6063858991788287, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent drove forward instead of right. (rewarded 1.61)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 1.27665569084
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.2766556908375164, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent followed the waypoint right. (rewarded 1.28)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 1.42296587241
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': 1.422965872414518, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.42)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: left, reward: -9.71647201312
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': -9.716472013118564, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.72)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 1.02268562275
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.02268562274549, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.02)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 2.03871563352
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': 2.038715633520567, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.04)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: left, reward: 1.69463643073
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': 1.694636430729801, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.69)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 36
\-------------------------

Environment.reset(): Trial set up with start = (3, 3), destination = (1, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.5827; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 2.48260610952
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.4826061095215244, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.48)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 2.66569732689
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.665697326893611, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.67)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 1.33820079259
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.3382007925871549, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.34)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: forward, reward: 1.45632217203
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 1.456322172032482, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent followed the waypoint forward. (rewarded 1.46)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 1.62661080006
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.6266108000618156, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.63)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: right, reward: 1.02535021797
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 1.0253502179651073, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 1.03)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: left, reward: -19.9919081069
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 19, 't': 6, 'action': 'left', 'reward': -19.99190810690218, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.99)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: None, reward: 2.89909811164
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.8990981116383177, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.90)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: None, reward: 2.86934290856
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.8693429085587923, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.87)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: right, reward: 0.419171448289
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 0.4191714482892255, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.42)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 2.02582642095
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 15, 't': 10, 'action': None, 'reward': 2.0258264209458234, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.03)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: -4.37593280748
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 14, 't': 11, 'action': None, 'reward': -4.375932807484396, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.38)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: left, reward: 2.55003628727
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 2.5500362872718414, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent followed the waypoint left. (rewarded 2.55)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: forward, reward: 1.08585513887
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 1.0858551388660713, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 1.09)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.06470610767
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.0647061076679218, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.06)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.14497611964
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 10, 't': 15, 'action': None, 'reward': 1.1449761196407158, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.14)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: left, reward: -20.9092875405
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 9, 't': 16, 'action': 'left', 'reward': -20.90928754052394, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.91)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: -5.84961367737
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 17, 'action': None, 'reward': -5.84961367737469, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.85)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: left, reward: 1.47138937908
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 18, 'action': 'left', 'reward': 1.4713893790782429, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.47)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.91029473373
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 6, 't': 19, 'action': None, 'reward': 1.9102947337293676, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.91)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.24581295401
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 20, 'action': None, 'reward': 1.2458129540132776, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.25)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 1.31311136263
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': 1.3131113626256627, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.31)
12% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 37
\-------------------------

Environment.reset(): Trial set up with start = (6, 3), destination = (2, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.5741; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5741; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 1.1241899675
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.1241899674976954, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.12)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: 1.54802991867
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.5480299186654407, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 1.55)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: forward, reward: -9.79888842717
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': -9.79888842716752, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.80)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: forward, reward: 2.12158532351
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.1215853235127384, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.12)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: left, reward: -10.1836712684
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': -10.183671268355754, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.18)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 2.1146683664
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.114668366401472, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.11)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 1.91680816692
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.9168081669172183, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.92)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 2.60735734636
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.6073573463555277, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent followed the waypoint forward. (rewarded 2.61)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.523685851
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.5236858509987332, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.52)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: forward, reward: -0.149173990174
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': -0.149173990174148, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded -0.15)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: left, reward: -19.6216558695
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': -19.62165586952647, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.62)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: left, reward: -20.8475804316
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': -20.847580431599496, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.85)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: forward, reward: 0.447286335896
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 0.4472863358958925, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 0.45)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: right, reward: -0.0549383992073
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': -0.05493839920728261, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove right instead of left. (rewarded -0.05)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: right, reward: 2.24995906955
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 2.2499590695544676, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.25)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: None, reward: 1.0398021514
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.0398021513978852, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.04)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: None, reward: 0.554185697782
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': None, 'reward': 0.5541856977822746, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.55)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: forward, reward: 0.989189953355
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 0.9891899533552625, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent drove forward instead of right. (rewarded 0.99)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: 0.0771987951959
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.07719879519589612, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.08)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: forward, reward: -9.04530984001
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': -9.045309840005231, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.05)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 38
\-------------------------

Environment.reset(): Trial set up with start = (8, 3), destination = (4, 6), deadline = 35
Simulating trial. . . 
epsilon = 0.5655; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5655; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5655; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5655; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5655; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: left, reward: -10.8681387241
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 35, 't': 0, 'action': 'left', 'reward': -10.868138724078209, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.87)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 0.142946706015
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 34, 't': 1, 'action': None, 'reward': 0.14294670601473403, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.14)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 1.48365585391
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 33, 't': 2, 'action': 'right', 'reward': 1.4836558539088958, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.48)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.02782174677
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 32, 't': 3, 'action': 'right', 'reward': 1.0278217467731572, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 1.03)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.24333061206
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 31, 't': 4, 'action': None, 'reward': 1.24333061206324, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.24)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 0.694949499002
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 30, 't': 5, 'action': 'right', 'reward': 0.6949494990024903, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.69)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: left, reward: 2.20963063407
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 29, 't': 6, 'action': 'left', 'reward': 2.20963063407054, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.21)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: right, reward: 0.954793793291
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 28, 't': 7, 'action': 'right', 'reward': 0.9547937932910161, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.95)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: forward, reward: 1.40433492988
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 27, 't': 8, 'action': 'forward', 'reward': 1.404334929880437, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.40)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.84919292769
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 26, 't': 9, 'action': None, 'reward': 1.849192927686777, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.85)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.13337554576
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 25, 't': 10, 'action': None, 'reward': 1.1333755457584946, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.13)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 0.200925360197
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 24, 't': 11, 'action': 'right', 'reward': 0.20092536019698748, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove right instead of forward. (rewarded 0.20)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.10350814977
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 12, 'action': None, 'reward': 1.1035081497717778, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.10)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: left, reward: -9.87520722674
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 22, 't': 13, 'action': 'left', 'reward': -9.875207226741018, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent attempted driving left through a red light. (rewarded -9.88)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: 0.733575113334
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 21, 't': 14, 'action': 'right', 'reward': 0.7335751133343008, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.73)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: left, reward: -39.6639399447
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 15, 'action': 'left', 'reward': -39.66393994465685, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.66)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: right, reward: 2.48008922361
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 16, 'action': 'right', 'reward': 2.480089223612702, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.48)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 0.614204025107
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 18, 't': 17, 'action': None, 'reward': 0.6142040251066213, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.61)
49% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: forward, reward: -39.2456360353
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 17, 't': 18, 'action': 'forward', 'reward': -39.24563603530671, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.25)
46% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: right, reward: 1.09848751594
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 19, 'action': 'right', 'reward': 1.098487515939074, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.10)
43% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: forward, reward: -9.2100026644
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 15, 't': 20, 'action': 'forward', 'reward': -9.210002664401914, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent attempted driving forward through a red light. (rewarded -9.21)
40% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 0.0251471645809
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'forward'), 'deadline': 14, 't': 21, 'action': 'right', 'reward': 0.02514716458088251, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'forward')
Agent drove right instead of forward. (rewarded 0.03)
37% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.20439322921
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 22, 'action': None, 'reward': 1.2043932292058015, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.20)
34% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: forward, reward: -40.5642884242
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 23, 'action': 'forward', 'reward': -40.564288424231705, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.56)
31% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.20777110483
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 24, 'action': None, 'reward': 1.2077711048297628, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.21)
29% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: 0.0132734869413
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 10, 't': 25, 'action': 'right', 'reward': 0.013273486941268287, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.01)
26% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: right, reward: 1.12534666869
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 9, 't': 26, 'action': 'right', 'reward': 1.1253466686945361, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.13)
23% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 1.03325026376
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 8, 't': 27, 'action': None, 'reward': 1.0332502637617291, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.03)
20% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: right, reward: 1.21451004044
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 7, 't': 28, 'action': 'right', 'reward': 1.2145100404367586, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.21)
17% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 0.619172808905
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 6, 't': 29, 'action': 'right', 'reward': 0.6191728089054994, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.62)
14% of time remaining to reach destination.

/-------------------
| Step 30 Results
\-------------------

Environment.step(): t = 30
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: left, reward: 2.03414762546
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 5, 't': 30, 'action': 'left', 'reward': 2.034147625460675, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.03)
11% of time remaining to reach destination.

/-------------------
| Step 31 Results
\-------------------

Environment.step(): t = 31
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: None, reward: 1.47439684827
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 4, 't': 31, 'action': None, 'reward': 1.4743968482743846, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.47)
9% of time remaining to reach destination.

/-------------------
| Step 32 Results
\-------------------

Environment.step(): t = 32
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: None, reward: 1.13313844084
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'right'), 'deadline': 3, 't': 32, 'action': None, 'reward': 1.1331384408421157, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'right')
Agent properly idled at a red light. (rewarded 1.13)
6% of time remaining to reach destination.

/-------------------
| Step 33 Results
\-------------------

Environment.step(): t = 33
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: left, reward: -19.0290211991
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'right', 'left'), 'deadline': 2, 't': 33, 'action': 'left', 'reward': -19.02902119905312, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'left')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.03)
3% of time remaining to reach destination.

/-------------------
| Step 34 Results
\-------------------

Environment.step(): t = 34
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: right, reward: -0.632801733775
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 1, 't': 34, 'action': 'right', 'reward': -0.6328017337754064, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded -0.63)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 39
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (6, 3), deadline = 35
Simulating trial. . . 
epsilon = 0.5571; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 2.81256920524
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 35, 't': 0, 'action': 'right', 'reward': 2.81256920523754, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.81)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: left, reward: -40.2327400547
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 34, 't': 1, 'action': 'left', 'reward': -40.23274005474511, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.23)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.87611736611
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 33, 't': 2, 'action': None, 'reward': 1.876117366113566, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.88)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 0.418439272201
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 32, 't': 3, 'action': 'right', 'reward': 0.4184392722005972, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.42)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: forward, reward: -10.52940063
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 31, 't': 4, 'action': 'forward', 'reward': -10.52940063004732, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.53)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: left, reward: 2.07146849858
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 30, 't': 5, 'action': 'left', 'reward': 2.0714684985784246, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.07)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.43607039657
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 29, 't': 6, 'action': None, 'reward': 1.436070396574896, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.44)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.08510021694
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 28, 't': 7, 'action': None, 'reward': 1.0851002169352824, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.09)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: left, reward: -39.0608124129
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'right', 'left'), 'deadline': 27, 't': 8, 'action': 'left', 'reward': -39.0608124128576, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.06)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: right, reward: -0.0223262786227
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 26, 't': 9, 'action': 'right', 'reward': -0.022326278622695872, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent drove right instead of forward. (rewarded -0.02)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 1.46877296758
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 25, 't': 10, 'action': None, 'reward': 1.4687729675813106, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.47)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: 1.08603519092
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 24, 't': 11, 'action': 'forward', 'reward': 1.0860351909237447, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.09)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: -0.0509579941098
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 12, 'action': 'right', 'reward': -0.05095799410979607, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded -0.05)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: -9.59163839058
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 22, 't': 13, 'action': 'left', 'reward': -9.591638390576934, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.59)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: -10.8523712165
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 21, 't': 14, 'action': 'left', 'reward': -10.852371216531917, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.85)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.58485736017
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 20, 't': 15, 'action': 'right', 'reward': 1.584857360172356, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.58)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 1.43629725577
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 16, 'action': 'right', 'reward': 1.436297255768378, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.44)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: forward, reward: 2.53354255611
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 17, 'action': 'forward', 'reward': 2.533542556108075, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.53)
49% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 2.34548701509
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 18, 'action': None, 'reward': 2.345487015093971, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.35)
46% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: left, reward: 1.21865530304
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 19, 'action': 'left', 'reward': 1.2186553030449385, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded 1.22)
43% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 0.27209865854
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 15, 't': 20, 'action': None, 'reward': 0.2720986585401055, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.27)
40% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: 1.49748286379
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 14, 't': 21, 'action': 'left', 'reward': 1.4974828637878768, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent drove left instead of right. (rewarded 1.50)
37% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: left, reward: 1.28627537896
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 13, 't': 22, 'action': 'left', 'reward': 1.2862753789633747, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.29)
34% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: left, reward: 0.994482973272
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 23, 'action': 'left', 'reward': 0.9944829732715113, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.99)
31% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: forward, reward: 2.54015731406
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 11, 't': 24, 'action': 'forward', 'reward': 2.5401573140596616, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.54)
29% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: forward, reward: 0.578033081289
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 10, 't': 25, 'action': 'forward', 'reward': 0.578033081288728, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 0.58)
26% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: left, reward: 0.308224685285
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 9, 't': 26, 'action': 'left', 'reward': 0.3082246852846777, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.31)
23% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: -4.7166707135
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 27, 'action': None, 'reward': -4.716670713501119, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.72)
20% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: left, reward: -39.1497089157
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 7, 't': 28, 'action': 'left', 'reward': -39.14970891567864, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.15)
17% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 2.20886861668
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 29, 'action': None, 'reward': 2.2088686166810954, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
14% of time remaining to reach destination.

/-------------------
| Step 30 Results
\-------------------

Environment.step(): t = 30
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 1.36042555573
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 30, 'action': None, 'reward': 1.3604255557292992, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.36)
11% of time remaining to reach destination.

/-------------------
| Step 31 Results
\-------------------

Environment.step(): t = 31
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: left, reward: 1.34185248314
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 31, 'action': 'left', 'reward': 1.3418524831400418, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.34)
9% of time remaining to reach destination.

/-------------------
| Step 32 Results
\-------------------

Environment.step(): t = 32
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: left, reward: 0.930341311225
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 3, 't': 32, 'action': 'left', 'reward': 0.9303413112245946, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.93)
6% of time remaining to reach destination.

/-------------------
| Step 33 Results
\-------------------

Environment.step(): t = 33
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 0.699020897466
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 2, 't': 33, 'action': None, 'reward': 0.6990208974655132, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 0.70)
3% of time remaining to reach destination.

/-------------------
| Step 34 Results
\-------------------

Environment.step(): t = 34
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: forward, reward: -39.6976297066
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 1, 't': 34, 'action': 'forward', 'reward': -39.697629706649835, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.70)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 40
\-------------------------

Environment.reset(): Trial set up with start = (7, 6), destination = (1, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.5488; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5488; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5488; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: None, reward: -4.04599652138
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': -4.045996521383804, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.05)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: right, reward: 0.0370798666298
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.037079866629763925, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 0.04)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: left, reward: 0.528473303879
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 0.528473303878863, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.53)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: 2.31351207544
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.3135120754434877, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.31)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: -4.83193896474
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': -4.831938964740172, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.83)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: forward, reward: 0.363513928372
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 0.36351392837191865, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.36)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: left, reward: 1.33607292599
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.3360729259891961, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.34)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 1.72949396513
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.7294939651307262, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.73)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: -0.15235661805
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': -0.15235661804961442, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded -0.15)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: None, reward: 2.52937934873
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.529379348734875, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.53)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: None, reward: 1.25897394352
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.2589739435158935, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.26)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: left, reward: -9.36079998259
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': -9.360799982590702, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -9.36)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: forward, reward: -10.5076941767
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -10.50769417668766, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.51)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: 2.14084732286
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 2.1408473228561196, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.14)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.52015737563
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.520157375631584, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.52)
25% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 41
\-------------------------

Environment.reset(): Trial set up with start = (4, 6), destination = (1, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.5406; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: right, reward: 2.14612547492
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 2.1461254749199288, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.15)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: left, reward: -10.3643542096
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 29, 't': 1, 'action': 'left', 'reward': -10.364354209551774, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -10.36)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 0.543191733388
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 0.5431917333877508, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent drove right instead of forward. (rewarded 0.54)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 1.09149446045
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.0914944604519257, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.09)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.05878923633
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 2.0587892363310223, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.06)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 1.17682681184
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 1.1768268118375, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove right instead of left. (rewarded 1.18)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: left, reward: -10.4643667705
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 24, 't': 6, 'action': 'left', 'reward': -10.464366770546352, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.46)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: forward, reward: 1.38549257573
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 1.3854925757251135, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.39)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: 1.37985923809
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 22, 't': 8, 'action': 'forward', 'reward': 1.3798592380924695, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.38)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: -9.65146232347
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': -9.651462323472238, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.65)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: -9.2069563543
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': -9.206956354299122, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.21)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: forward, reward: 2.72911027026
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': 2.7291102702645933, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.73)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 2.50963757642
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.5096375764221324, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.51)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: right, reward: 1.00515284187
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 1.0051528418736584, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.01)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: left, reward: 1.28658417241
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 1.2865841724094618, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.29)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: None, reward: 2.70538689112
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 15, 'action': None, 'reward': 2.70538689111755, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.71)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: right, reward: 0.645852189815
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'right', 'reward': 0.6458521898154301, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.65)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: left, reward: -20.611811307
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 13, 't': 17, 'action': 'left', 'reward': -20.6118113069637, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.61)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: None, reward: -4.64017092863
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 12, 't': 18, 'action': None, 'reward': -4.640170928626963, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.64)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: right, reward: 0.191110605899
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 11, 't': 19, 'action': 'right', 'reward': 0.19111060589926698, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.19)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: forward, reward: -0.192323610997
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 10, 't': 20, 'action': 'forward', 'reward': -0.19232361099650164, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove forward instead of left. (rewarded -0.19)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: right, reward: -0.0192175253762
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 9, 't': 21, 'action': 'right', 'reward': -0.019217525376160283, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove right instead of left. (rewarded -0.02)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 2.02006733964
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 8, 't': 22, 'action': 'right', 'reward': 2.020067339640215, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.02)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: forward, reward: 2.25578133548
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 23, 'action': 'forward', 'reward': 2.2557813354771543, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.26)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: right, reward: 0.654440128387
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 6, 't': 24, 'action': 'right', 'reward': 0.6544401283868988, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 0.65)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: forward, reward: 1.11844582607
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 5, 't': 25, 'action': 'forward', 'reward': 1.1184458260725394, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove forward instead of left. (rewarded 1.12)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 0.451591750451
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 4, 't': 26, 'action': None, 'reward': 0.45159175045093547, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.45)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 0.732613897346
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 3, 't': 27, 'action': None, 'reward': 0.7326138973464971, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.73)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: forward, reward: -9.07583321786
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 2, 't': 28, 'action': 'forward', 'reward': -9.075833217859875, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.08)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: left, reward: 1.59752421069
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 1, 't': 29, 'action': 'left', 'reward': 1.5975242106935064, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.60)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 42
\-------------------------

Environment.reset(): Trial set up with start = (6, 5), destination = (5, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.5326; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5326; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5326; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: right, reward: 2.23775947125
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.2377594712535105, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.24)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: right, reward: 2.77502764471
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.775027644708169, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.78)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: left, reward: -10.3293496235
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': -10.329349623493407, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -10.33)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: left, reward: -10.4465770245
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -10.446577024541911, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.45)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: left, reward: 1.20117756248
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.2011775624828964, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.20)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: forward, reward: -40.0617710085
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'right', 'left'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': -40.06177100846972, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'left')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.06)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: right, reward: 0.00653296217181
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.006532962171808876, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.01)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: left, reward: 2.8108563487
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 2.8108563487013436, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.81)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: -4.0515652393
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': -4.051565239301542, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.05)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: 2.58733287319
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.5873328731920573, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.59)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: 1.3438647922
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.3438647922030327, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.34)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: 1.41080034547
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.4108003454650544, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.41)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: forward, reward: -40.753362949
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -40.7533629489798, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.75)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: -4.35773462773
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 7, 't': 13, 'action': None, 'reward': -4.357734627729382, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.36)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: -4.17793921504
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 6, 't': 14, 'action': None, 'reward': -4.177939215042536, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.18)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: right, reward: -0.467486363648
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 5, 't': 15, 'action': 'right', 'reward': -0.4674863636482649, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove right instead of left. (rewarded -0.47)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: left, reward: -10.5549823052
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'forward', 'right'), 'deadline': 4, 't': 16, 'action': 'left', 'reward': -10.554982305203369, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'right')
Agent attempted driving left through a red light. (rewarded -10.55)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: right, reward: 1.04276109145
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 1.0427610914457353, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.04)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: -0.46116740602
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': -0.4611674060203972, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded -0.46)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: left, reward: 0.183184875993
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': 0.18318487599320254, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.18)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 43
\-------------------------

Environment.reset(): Trial set up with start = (3, 7), destination = (4, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.5247; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: right, reward: 1.25143144259
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.251431442593098, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.25)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.1777826533
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.1777826533016968, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.18)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: right, reward: 2.61112886724
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.611128867241403, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.61)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: None, reward: 1.94567333882
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.9456733388153373, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.95)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: None, reward: 2.37700792318
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.3770079231778096, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.38)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: forward, reward: 1.77976524992
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.7797652499173429, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 1.78)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: left, reward: 2.65190941184
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 2.6519094118393274, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.65)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: -4.91922156136
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 13, 't': 7, 'action': None, 'reward': -4.919221561355392, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -4.92)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: -5.3292652432
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': None, 'reward': -5.329265243195721, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -5.33)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: left, reward: 2.14320037697
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.1432003769653782, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.14)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: right, reward: 2.47240314243
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 2.472403142428148, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.47)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 44
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (4, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.5169; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: -10.0396457338
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': -10.039645733781752, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.04)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.0917681516535
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.09176815165354968, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.09)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: right, reward: 0.181519755319
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.18151975531854248, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 0.18)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: -5.28734600608
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': -5.28734600608421, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.29)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: -5.25415804267
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 4, 'action': None, 'reward': -5.254158042668432, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.25)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 2.78301060088
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.7830106008824664, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.78)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 2.81517346726
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.815173467259468, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.82)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 2.60462707683
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.6046270768319473, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.60)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: -9.62733564356
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': -9.6273356435579, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.63)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: 0.817288417885
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 0.8172884178850532, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.82)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: right, reward: 1.00611774751
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.006117747512436, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 1.01)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: left, reward: 1.95111633769
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.9511163376884602, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.95)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: left, reward: -40.3651579886
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 12, 'action': 'left', 'reward': -40.365157988618584, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.37)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: left, reward: 1.57039104173
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.570391041729101, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.57)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: left, reward: 1.38734132226
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 6, 't': 14, 'action': 'left', 'reward': 1.3873413222583801, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove left instead of forward. (rewarded 1.39)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: left, reward: -40.5599805634
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': -40.55998056344377, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.56)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 1.2480967474
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 1.248096747399911, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.25)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 0.819187597258
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 0.8191875972579139, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.82)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: forward, reward: 2.06965745919
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 2, 't': 18, 'action': 'forward', 'reward': 2.069657459190994, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.07)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: right, reward: 1.17057771077
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 1.1705777107738708, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.17)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 45
\-------------------------

Environment.reset(): Trial set up with start = (6, 2), destination = (2, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.5092; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.5092; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: None, reward: 2.3660808471
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.3660808471035164, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.37)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: None, reward: 1.19140007335
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.1914000733472492, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.19)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: right, reward: 1.73170747665
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.7317074766491736, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 1.73)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 1.25424662622
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.2542466262150462, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.25)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: right, reward: 0.979754464945
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.9797544649453888, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove right instead of left. (rewarded 0.98)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.58806251902
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.5880625190219466, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.59)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.1729695726
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.172969572595793, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.17)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: 2.19315316625
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.1931531662464563, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.19)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: -9.29763167739
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': -9.29763167739228, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.30)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 1.22330099575
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.2233009957458987, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.22)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 1.90101593644
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.9010159364421335, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.90)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: forward, reward: 1.41090210041
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 1.4109021004070816, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.41)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: 2.44059123246
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 2.4405912324608314, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.44)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 1.70959928699
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.7095992869906447, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.71)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 0.571697999001
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 0.57169799900061, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.57)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: forward, reward: -9.48161099092
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -9.481610990917167, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.48)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: None, reward: 2.21633560836
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': None, 'reward': 2.216335608360561, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.22)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: left, reward: 1.04555908252
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'left', 'reward': 1.0455590825197227, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.05)
10% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 46
\-------------------------

Environment.reset(): Trial set up with start = (6, 2), destination = (2, 4), deadline = 30
Simulating trial. . . 
epsilon = 0.5016; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: right, reward: 1.99447384425
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 1.9944738442477525, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.99)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: 0.622636429723
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 0.6226364297226908, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 0.62)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: right, reward: 0.783174472559
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 0.7831744725591391, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.78)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: right, reward: 1.34489122158
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 1.3448912215805984, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.34)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: None, reward: -4.25665264432
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 26, 't': 4, 'action': None, 'reward': -4.256652644321681, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.26)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: left, reward: -20.0885369469
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': 'forward'}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 25, 't': 5, 'action': 'left', 'reward': -20.08853694689237, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.09)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: forward, reward: 1.12749341145
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 1.1274934114536177, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.13)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: left, reward: -9.10490891772
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 23, 't': 7, 'action': 'left', 'reward': -9.10490891772286, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent attempted driving left through a red light. (rewarded -9.10)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 2.01842339072
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.018423390715223, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.02)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: forward, reward: -9.72404066589
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': -9.724040665890954, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.72)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: left, reward: -0.0270525818179
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': -0.02705258181787329, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove left instead of forward. (rewarded -0.03)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 1.53549010658
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 1.5354901065837243, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent followed the waypoint right. (rewarded 1.54)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: left, reward: 0.536770759236
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 18, 't': 12, 'action': 'left', 'reward': 0.5367707592360002, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove left instead of forward. (rewarded 0.54)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: forward, reward: -40.3208269073
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': -40.32082690734004, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.32)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: right, reward: 1.26002563057
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 1.2600256305685809, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.26)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: left, reward: 1.18292411977
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 15, 't': 15, 'action': 'left', 'reward': 1.1829241197738165, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.18)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: 1.43280033506
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'right', 'reward': 1.4328003350592646, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.43)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.3063732319
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 13, 't': 17, 'action': None, 'reward': 1.306373231896625, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.31)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.55303363638
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 18, 'action': None, 'reward': 1.553033636377006, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.55)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: left, reward: -9.17686351348
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 11, 't': 19, 'action': 'left', 'reward': -9.17686351348189, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent attempted driving left through a red light. (rewarded -9.18)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.73336110673
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.7333611067284072, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.73)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: 0.862990120445
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'left', 'reward': 0.8629901204447856, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.86)
27% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 47
\-------------------------

Environment.reset(): Trial set up with start = (8, 2), destination = (2, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.4941; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4941; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 1.64456833936
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.6445683393567427, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.64)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 0.829645106908
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 19, 't': 1, 'action': None, 'reward': 0.8296451069075924, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 0.83)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: forward, reward: -9.01209600394
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': -9.01209600394377, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.01)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 0.745201478398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 0.7452014783983266, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.75)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: left, reward: -10.161993569
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': -10.161993568967494, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.16)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: 2.47496656549
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 2.474966565493262, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent followed the waypoint right. (rewarded 2.47)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: None, reward: 1.95590309939
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.9559030993869364, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.96)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: right, reward: 1.79975854664
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.7997585466406452, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.80)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: 2.76961129416
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.7696112941641458, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.77)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: 2.33818382967
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.3381838296739232, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.34)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: -5.10286280299
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': None, 'reward': -5.102862802993264, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.10)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 0.275868728413
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.2758687284127268, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.28)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: -9.27271659169
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 8, 't': 12, 'action': 'left', 'reward': -9.27271659169106, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -9.27)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: 1.25744993232
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.2574499323222335, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.26)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: 1.92514138976
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': 1.9251413897579464, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.93)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: -5.1641459029
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': -5.164145902897479, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.16)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: -5.58836352723
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 16, 'action': None, 'reward': -5.588363527234515, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.59)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 1.9788418262
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.9788418261994825, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.98)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: -10.0856580449
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 18, 'action': 'left', 'reward': -10.085658044859855, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.09)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: -5.75289817646
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 1, 't': 19, 'action': None, 'reward': -5.752898176461836, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.75)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 48
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (8, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.4868; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: left, reward: -20.3236078535
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': -20.32360785350156, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.32)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 1.40833847049
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.4083384704890798, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove right instead of left. (rewarded 1.41)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 2.75626711744
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 2.756267117438934, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.76)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: forward, reward: 2.72126647516
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.7212664751642937, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.72)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 1.47815557427
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.478155574267945, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.48)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: forward, reward: 1.22572029875
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.225720298745622, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.23)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 0.219508470845
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.21950847084474967, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.22)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 1.08464129767
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.0846412976684707, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.08)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 2.52706558596
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.527065585960049, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.53)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: -0.0576759401674
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': -0.05767594016743871, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded -0.06)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.33389620953
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.3338962095296638, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.33)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: -9.26287006137
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': -9.262870061369307, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.26)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: -0.0656641331615
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': -0.0656641331614567, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded -0.07)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: forward, reward: -39.59592041
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': -39.59592041001884, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.60)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 0.799049250614
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 0.7990492506142046, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.80)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 1.5138085244
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 1.5138085244018915, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.51)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: -5.94835383864
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 4, 't': 16, 'action': None, 'reward': -5.948353838637045, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.95)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 0.593873801468
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 3, 't': 17, 'action': None, 'reward': 0.5938738014679172, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.59)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 0.866538975009
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.8665389750087538, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.87)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 0.380975714841
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.38097571484083237, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.38)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 49
\-------------------------

Environment.reset(): Trial set up with start = (7, 5), destination = (5, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.4795; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: right, reward: 2.63930175957
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.639301759567659, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.64)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 1.76583939368
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.7658393936770875, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.77)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: 1.48310884085
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.4831088408454454, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.48)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: -20.2982090969
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': -20.29820909688832, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.30)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: 2.06782461072
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.0678246107238447, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.07)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: -5.9170514328
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': -5.917051432795119, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.92)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: 1.09116214867
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.0911621486720342, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.09)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: right, reward: 1.58509306517
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.58509306517081, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 1.59)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: left, reward: 1.5736679501
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 1.573667950104515, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 1.57)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 2.29746187811
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.2974618781122933, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.30)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: -19.032080738
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': -19.032080737997966, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.03)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 1.91216519438
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.9121651943765292, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.91)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 1.9351633232
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.9351633231978118, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.94)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: left, reward: 2.14416046989
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 2.1441604698860415, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.14)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: 2.43568006272
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': 2.435680062715801, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.44)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: -4.92030378987
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 5, 't': 15, 'action': None, 'reward': -4.920303789869491, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.92)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: -40.4240427106
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': -40.424042710594634, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.42)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 1.62737380794
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.6273738079367597, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.63)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 0.961165676172
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.9611656761722154, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.96)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: forward, reward: 0.961249926526
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': 0.9612499265261572, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.96)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 50
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (8, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.4724; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 0.0707861845031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 0.07078618450306196, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.07)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: forward, reward: -10.9708943792
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': -10.970894379198246, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -10.97)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: right, reward: 1.41956431436
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.4195643143626338, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.42)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 0.300705305375
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 0.3007053053754478, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded 0.30)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: left, reward: 2.53149426607
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 2.531494266069478, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.53)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: forward, reward: -40.0379288291
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': -40.037928829134586, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.04)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: left, reward: -9.4089065433
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': -9.408906543299162, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -9.41)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 2.49944518568
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'right'), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 2.49944518568442, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'right')
Agent followed the waypoint forward. (rewarded 2.50)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 1.73111292722
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.7311129272164227, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.73)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 2.85355300477
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 2.85355300477394, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.85)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 51
\-------------------------

Environment.reset(): Trial set up with start = (4, 4), destination = (6, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.4653; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4653; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: None, reward: -5.40775804143
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 0, 'action': None, 'reward': -5.407758041427233, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.41)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: left, reward: 2.72988697319
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 2.7298869731851214, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.73)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 2.78083841976
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.78083841976436, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.78)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 2.83035377632
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.8303537763248108, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.83)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 2.08856455624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.088564556236717, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.09)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: forward, reward: 2.26863211459
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.268632114590891, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.27)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: None, reward: 2.66454763991
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.66454763991299, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.66)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: right, reward: 1.8459164038
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.8459164037971825, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.85)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: right, reward: 0.606003786361
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.6060037863613804, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.61)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: left, reward: -10.8526394873
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': -10.852639487272263, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.85)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: left, reward: 2.44956051122
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.449560511217477, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.45)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 1.98598586635
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.9859858663466845, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.99)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 0.614020372935
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.6140203729350795, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.61)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 1.52809765979
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.5280976597867215, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.53)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 1.84856253309
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.8485625330852131, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.85)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: 0.414059833147
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': 0.4140598331473566, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 0.41)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.12079243285
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 16, 'action': None, 'reward': 1.120792432850761, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.12)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 0.239243518348
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 0.23924351834802382, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent drove right instead of left. (rewarded 0.24)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 1.8009591037
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 1.8009591037013832, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.80)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: 0.828245244693
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.828245244692825, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.83)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 52
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (3, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.4584; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4584; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: None, reward: -5.39949698213
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': -5.399496982126017, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.40)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: forward, reward: 2.84325701803
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 2.8432570180264456, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.84)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: forward, reward: -9.29480165976
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': -9.294801659759983, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.29)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 2.09162978649
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.0916297864937636, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.09)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 1.51277929452
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.5127792945243348, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.51)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: right, reward: 1.55328907406
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.5532890740642051, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.55)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: forward, reward: -10.5378903944
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': -10.537890394439271, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.54)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: right, reward: 0.262358568357
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.26235856835681126, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.26)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: right, reward: -0.131543104518
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': -0.13154310451801365, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded -0.13)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: forward, reward: 1.48191477603
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.4819147760290976, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent drove forward instead of right. (rewarded 1.48)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: None, reward: 1.60650982168
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.6065098216765312, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.61)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: None, reward: 0.536819112473
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 9, 't': 11, 'action': None, 'reward': 0.5368191124727346, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.54)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: right, reward: 1.160724287
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'left'), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.1607242869953647, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'left')
Agent followed the waypoint right. (rewarded 1.16)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: right, reward: 1.69414539553
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 1.6941453955307653, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.69)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: None, reward: 1.0304817356
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.0304817355955196, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.03)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: forward, reward: -10.5541208723
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -10.55412087230685, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.55)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: forward, reward: 1.36163144112
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 1.3616314411236123, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.36)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: None, reward: 2.08678506809
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 3, 't': 17, 'action': None, 'reward': 2.0867850680934543, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.09)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: None, reward: 1.29841906958
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.2984190695814182, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.30)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: right, reward: -0.827019824763
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 1, 't': 19, 'action': 'right', 'reward': -0.827019824763015, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded -0.83)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 53
\-------------------------

Environment.reset(): Trial set up with start = (6, 7), destination = (3, 4), deadline = 30
Simulating trial. . . 
epsilon = 0.4516; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 1.10306806305
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 1.1030680630460798, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.10)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: None, reward: -5.34201549552
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 29, 't': 1, 'action': None, 'reward': -5.34201549552044, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.34)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: right, reward: 2.64187842519
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 2.6418784251900327, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.64)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: forward, reward: 1.97991413337
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 27, 't': 3, 'action': 'forward', 'reward': 1.979914133365199, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent followed the waypoint forward. (rewarded 1.98)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: 1.10045697604
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.1004569760357081, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.10)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: -4.37047316871
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 25, 't': 5, 'action': None, 'reward': -4.3704731687072105, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.37)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: right, reward: 1.87546570803
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.8754657080306512, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent drove right instead of forward. (rewarded 1.88)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: 1.72418558775
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.7241855877467132, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.72)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: 2.04614826435
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.0461482643544207, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.05)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: forward, reward: 0.25253220445
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 0.2525322044503737, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 0.25)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: left, reward: 2.03747499242
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': 2.0374749924208295, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.04)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 2.47768320125
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 2.477683201252821, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.48)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.35293795213
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.3529379521287623, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.35)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 1.43086317772
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 1.4308631777170657, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 1.43)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: 0.834797335931
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 16, 't': 14, 'action': None, 'reward': 0.8347973359312546, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.83)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: 1.99340590541
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.9934059054057984, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.99)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: left, reward: 2.36568359077
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': 2.365683590773413, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.37)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: None, reward: 0.904795844882
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 13, 't': 17, 'action': None, 'reward': 0.9047958448824736, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.90)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: left, reward: -40.0094820796
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 12, 't': 18, 'action': 'left', 'reward': -40.009482079553706, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.01)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: None, reward: 0.777326865776
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 11, 't': 19, 'action': None, 'reward': 0.7773268657756669, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.78)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: None, reward: 2.51660202583
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 10, 't': 20, 'action': None, 'reward': 2.516602025830747, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.52)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: left, reward: 1.30402191694
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 9, 't': 21, 'action': 'left', 'reward': 1.3040219169403178, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.30)
27% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 54
\-------------------------

Environment.reset(): Trial set up with start = (8, 7), destination = (4, 4), deadline = 35
Simulating trial. . . 
epsilon = 0.4449; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: 2.28301633599
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 35, 't': 0, 'action': 'forward', 'reward': 2.2830163359859226, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.28)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: forward, reward: 1.33205010109
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 34, 't': 1, 'action': 'forward', 'reward': 1.3320501010935233, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.33)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: right, reward: 0.280321854329
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 33, 't': 2, 'action': 'right', 'reward': 0.2803218543290964, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.28)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: None, reward: 2.93014310433
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 32, 't': 3, 'action': None, 'reward': 2.930143104329282, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.93)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: -10.8487888173
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 31, 't': 4, 'action': 'forward', 'reward': -10.84878881727983, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.85)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: left, reward: 2.83600134313
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 30, 't': 5, 'action': 'left', 'reward': 2.8360013431324216, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.84)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: left, reward: 0.579527480984
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 29, 't': 6, 'action': 'left', 'reward': 0.5795274809841906, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 0.58)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 0.00794106973347
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 28, 't': 7, 'action': None, 'reward': 0.00794106973346731, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.01)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: right, reward: 2.05304171076
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 27, 't': 8, 'action': 'right', 'reward': 2.0530417107579533, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.05)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: right, reward: 2.87757517237
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 26, 't': 9, 'action': 'right', 'reward': 2.8775751723728775, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.88)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: forward, reward: -9.20122115377
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 25, 't': 10, 'action': 'forward', 'reward': -9.201221153766806, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.20)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: right, reward: -19.862516398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', 'right', 'forward'), 'deadline': 24, 't': 11, 'action': 'right', 'reward': -19.86251639799268, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.86)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: 2.37889654589
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 12, 'action': None, 'reward': 2.378896545894022, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.38)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: left, reward: 1.0286716944
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 22, 't': 13, 'action': 'left', 'reward': 1.0286716944030414, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.03)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: -4.18698445623
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 21, 't': 14, 'action': None, 'reward': -4.186984456233448, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.19)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 1.76319785
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 15, 'action': 'right', 'reward': 1.7631978499993195, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.76)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 2.39318814765
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 19, 't': 16, 'action': 'right', 'reward': 2.3931881476474888, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.39)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 1.13919804021
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 17, 'action': 'right', 'reward': 1.1391980402098514, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.14)
49% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 1.72249784142
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 18, 'action': 'right', 'reward': 1.722497841415653, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.72)
46% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 1.33153600672
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 19, 'action': None, 'reward': 1.331536006722549, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.33)
43% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 1.31158093278
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 15, 't': 20, 'action': 'right', 'reward': 1.3115809327805277, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.31)
40% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 2.28053301223
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 21, 'action': 'right', 'reward': 2.2805330122285605, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.28)
37% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 0.780580101728
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 22, 'action': None, 'reward': 0.7805801017280263, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.78)
34% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 1.21034124067
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 12, 't': 23, 'action': None, 'reward': 1.210341240671286, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.21)
31% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 0.771966544724
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 11, 't': 24, 'action': None, 'reward': 0.7719665447237063, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.77)
29% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 1.39175685481
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 10, 't': 25, 'action': 'right', 'reward': 1.3917568548063928, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.39)
26% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: -0.0612121259743
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 9, 't': 26, 'action': None, 'reward': -0.061212125974341, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded -0.06)
23% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 1.78703032
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 8, 't': 27, 'action': 'right', 'reward': 1.7870303199989857, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.79)
20% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 0.970614145576
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 7, 't': 28, 'action': 'right', 'reward': 0.9706141455758679, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.97)
17% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: forward, reward: -0.0297811090025
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 6, 't': 29, 'action': 'forward', 'reward': -0.029781109002471884, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded -0.03)
14% of time remaining to reach destination.

/-------------------
| Step 30 Results
\-------------------

Environment.step(): t = 30
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: left, reward: 0.178433176281
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 5, 't': 30, 'action': 'left', 'reward': 0.17843317628134914, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded 0.18)
11% of time remaining to reach destination.

/-------------------
| Step 31 Results
\-------------------

Environment.step(): t = 31
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: left, reward: -20.332487674
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 4, 't': 31, 'action': 'left', 'reward': -20.33248767403362, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.33)
9% of time remaining to reach destination.

/-------------------
| Step 32 Results
\-------------------

Environment.step(): t = 32
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: None, reward: -5.16120920816
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 3, 't': 32, 'action': None, 'reward': -5.161209208160012, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.16)
6% of time remaining to reach destination.

/-------------------
| Step 33 Results
\-------------------

Environment.step(): t = 33
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: left, reward: 0.314716969871
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 2, 't': 33, 'action': 'left', 'reward': 0.3147169698706547, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded 0.31)
3% of time remaining to reach destination.

/-------------------
| Step 34 Results
\-------------------

Environment.step(): t = 34
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: left, reward: 0.167963150804
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 1, 't': 34, 'action': 'left', 'reward': 0.1679631508037156, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.17)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 55
\-------------------------

Environment.reset(): Trial set up with start = (4, 3), destination = (5, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.4382; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: forward, reward: 1.61869386754
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.618693867542264, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 1.62)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: forward, reward: -39.4169546843
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': -39.4169546842888, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.42)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 2.20154468569
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.2015446856940146, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.20)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 2.76427399128
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.764273991284141, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.76)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 2.8033897237
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.8033897236957284, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.80)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 0.116295452582
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 0.11629545258241047, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.12)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: forward, reward: -10.9133571451
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': -10.91335714512412, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -10.91)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: left, reward: 0.456758820781
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 0.4567588207807518, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.46)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: right, reward: 0.654164833874
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.6541648338744138, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 0.65)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: right, reward: 1.97905079855
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.9790507985543857, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.98)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: left, reward: 1.16616083047
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 1.1661608304674316, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.17)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 1.34921863759
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.349218637588603, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.35)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 2.01865321462
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 2.018653214624546, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.02)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: left, reward: 0.980381291339
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 0.9803812913386486, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 0.98)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: right, reward: 2.15617757524
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 2.156177575236846, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.16)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: right, reward: 1.33073196901
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 1.330731969006662, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.33)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 56
\-------------------------

Environment.reset(): Trial set up with start = (5, 6), destination = (8, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.4317; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: None, reward: -4.98004489507
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': -4.980044895072559, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.98)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: left, reward: 2.64849385918
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 24, 't': 1, 'action': 'left', 'reward': 2.6484938591830947, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.65)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 2.27928101455
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.279281014549004, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.28)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 2.0037735169
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.003773516896431, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.00)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 2.91127819648
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.9112781964803145, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.91)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: left, reward: 2.02107605766
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 2.021076057664357, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.02)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.58906582315
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.5890658231543477, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.59)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: -5.31256536328
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': None, 'reward': -5.312565363280635, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.31)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: 2.57977724083
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 2.5797772408305906, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.58)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.61166218757
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 9, 'action': None, 'reward': 2.6116621875657886, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.61)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 1.10789080639
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.1078908063856423, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.11)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: forward, reward: 1.13329347112
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.1332934711228715, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.13)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 2.10791941905
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 2.1079194190454915, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.11)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 57
\-------------------------

Environment.reset(): Trial set up with start = (7, 4), destination = (2, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.4253; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: 2.38634617516
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 2.3863461751560546, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 2.39)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: forward, reward: 2.17105837931
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 29, 't': 1, 'action': 'forward', 'reward': 2.1710583793143456, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.17)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: left, reward: 0.550179532193
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 28, 't': 2, 'action': 'left', 'reward': 0.5501795321933131, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.55)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: left, reward: -39.6369858915
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 27, 't': 3, 'action': 'left', 'reward': -39.6369858914838, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.64)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: 0.773833898098
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 26, 't': 4, 'action': 'left', 'reward': 0.7738338980979168, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent drove left instead of right. (rewarded 0.77)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.11397328418
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 25, 't': 5, 'action': None, 'reward': 1.1139732841784098, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.11)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 1.1835001847
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.1835001847043678, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.18)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: 2.47738116637
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 2.4773811663717717, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.48)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: right, reward: -0.000154499066216
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 8, 'action': 'right', 'reward': -0.00015449906621622933, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded -0.00)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: 2.61419173076
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 21, 't': 9, 'action': None, 'reward': 2.614191730762707, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.61)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: -5.9324598838
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 10, 'action': None, 'reward': -5.932459883798763, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.93)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: forward, reward: 0.811239043227
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': 0.8112390432269464, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.81)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 0.667648599114
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 0.6676485991139981, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.67)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: left, reward: 0.85403631217
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 0.854036312169701, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent drove left instead of right. (rewarded 0.85)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: left, reward: 0.920364021131
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 0.9203640211305029, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 0.92)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 2.04998222864
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 15, 'action': None, 'reward': 2.049982228641663, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.05)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 1.5362632769
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.5362632769004747, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.54)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: left, reward: -19.3415561344
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 13, 't': 17, 'action': 'left', 'reward': -19.341556134424096, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.34)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: left, reward: 1.2348187323
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 12, 't': 18, 'action': 'left', 'reward': 1.23481873229659, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.23)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 1.49800964691
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 11, 't': 19, 'action': None, 'reward': 1.4980096469067674, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.50)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: right, reward: 1.48774636018
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 10, 't': 20, 'action': 'right', 'reward': 1.4877463601766396, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.49)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: -0.315274486086
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 9, 't': 21, 'action': 'right', 'reward': -0.31527448608583264, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove right instead of left. (rewarded -0.32)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 0.685583649347
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 22, 'action': None, 'reward': 0.6855836493469072, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.69)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: right, reward: 0.402471912752
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 0.4024719127520341, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.40)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: right, reward: -0.362334430125
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 6, 't': 24, 'action': 'right', 'reward': -0.36233443012477373, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded -0.36)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: right, reward: 1.55523618516
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 1.5552361851625054, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.56)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 2.01118778541
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 4, 't': 26, 'action': None, 'reward': 2.0111877854101783, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.01)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 2.2089105988
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 27, 'action': None, 'reward': 2.2089105988025945, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.44213323241
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 28, 'action': None, 'reward': 1.4421332324145089, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.44)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: -0.827302104444
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 1, 't': 29, 'action': 'right', 'reward': -0.8273021044442039, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded -0.83)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 58
\-------------------------

Environment.reset(): Trial set up with start = (8, 4), destination = (3, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.4190; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.1671200778
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.1671200777997852, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.17)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: -10.3078254535
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 29, 't': 1, 'action': 'forward', 'reward': -10.307825453469588, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent attempted driving forward through a red light. (rewarded -10.31)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 0.697100918976
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 28, 't': 2, 'action': None, 'reward': 0.6971009189759535, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.70)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.2633605178
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.2633605177984495, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.26)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.10533545301
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.1053354530106572, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.11)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 2.71815915161
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 2.718159151605271, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.72)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: -40.6306864155
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': -40.63068641553333, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.63)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 1.05005248333
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 1.0500524833263, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.05)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 1.60158238476
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.60158238475876, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.60)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: -40.5036828875
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 9, 'action': 'left', 'reward': -40.50368288745197, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.50)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: forward, reward: 2.81995392463
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 2.819953924633726, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.82)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: 1.7376571294
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 1.7376571294009069, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.74)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: right, reward: -19.3062113379
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 18, 't': 12, 'action': 'right', 'reward': -19.30621133792484, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.31)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: forward, reward: 2.59716594686
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 2.5971659468557746, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.60)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 2.02907014919
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 14, 'action': None, 'reward': 2.0290701491937364, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 2.03)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: forward, reward: 0.483239127344
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 15, 't': 15, 'action': 'forward', 'reward': 0.4832391273441997, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.48)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: left, reward: 0.905987120546
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': 0.9059871205461341, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.91)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 0.407281940005
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 0.4072819400047234, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.41)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 0.0523337889555
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 0.05233378895551355, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.05)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: left, reward: -39.8049108035
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'right', 'left'), 'deadline': 11, 't': 19, 'action': 'left', 'reward': -39.80491080345463, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.80)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: None, reward: -0.131260140909
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 20, 'action': None, 'reward': -0.13126014090917093, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded -0.13)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: None, reward: -4.99838084699
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 21, 'action': None, 'reward': -4.998380846989167, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.00)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 2.02908993047
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 8, 't': 22, 'action': 'right', 'reward': 2.0290899304736003, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.03)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: -4.85194335367
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 7, 't': 23, 'action': None, 'reward': -4.8519433536710785, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.85)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 0.736409248974
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 6, 't': 24, 'action': 'forward', 'reward': 0.7364092489737359, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 0.74)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.82937897803
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 1.8293789780273344, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.83)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: left, reward: -39.1963242775
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 4, 't': 26, 'action': 'left', 'reward': -39.196324277493346, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.20)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 0.830628314808
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 3, 't': 27, 'action': None, 'reward': 0.8306283148077878, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 0.83)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 0.32328826372
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 2, 't': 28, 'action': 'right', 'reward': 0.3232882637201905, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.32)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: left, reward: 0.818577041359
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 1, 't': 29, 'action': 'left', 'reward': 0.8185770413592506, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.82)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 59
\-------------------------

Environment.reset(): Trial set up with start = (6, 4), destination = (7, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.4127; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 1.57843251269
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.5784325126864756, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.58)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: right, reward: 2.57929144239
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.579291442391974, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.58)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: right, reward: 2.89803167482
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.8980316748199955, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.90)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: right, reward: 1.38885708864
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.388857088635358, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove right instead of left. (rewarded 1.39)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: -9.94150191295
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': -9.941501912949649, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.94)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: left, reward: 1.76143946379
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.7614394637935458, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 1.76)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.10819355337
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.1081935533692733, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.11)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.13130055498
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.131300554980686, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.13)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 2.49670989598
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.496709895977764, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.50)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: left, reward: -10.0817234352
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': -10.081723435190275, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.08)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: right, reward: 0.264915883053
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 0.2649158830531412, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent drove right instead of left. (rewarded 0.26)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: right, reward: 0.729486620443
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.7294866204425767, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.73)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: right, reward: 1.35647077665
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.3564707766482922, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.36)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: forward, reward: 1.46045050642
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.4604505064160096, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.46)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: right, reward: -0.190167596965
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': -0.19016759696456054, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded -0.19)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: right, reward: -0.0228455969826
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 5, 't': 15, 'action': 'right', 'reward': -0.022845596982574934, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent drove right instead of left. (rewarded -0.02)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: left, reward: 1.20143550988
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 1.2014355098792915, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 1.20)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 1.02443743531
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 1.0244374353104364, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.02)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.81573779207
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.8157377920726872, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.82)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: -9.37683544517
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -9.376835445166408, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.38)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 60
\-------------------------

Environment.reset(): Trial set up with start = (5, 4), destination = (3, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.4066; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: right, reward: 2.09261397865
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.0926139786459568, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.09)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 1.86237027643
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.8623702764258225, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.86)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: left, reward: -9.35582274841
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': -9.355822748411525, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.36)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 1.45750709361
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.4575070936069208, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.46)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 1.05539889593
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.0553988959341436, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.06)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 2.67104674592
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.6710467459151728, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.67)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: forward, reward: 1.78493403682
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.784934036824625, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.78)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: right, reward: -19.4194419782
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': 'right', 'reward': -19.419441978222103, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.42)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: left, reward: -10.4084088788
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'left', 'reward': -10.408408878805464, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.41)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: None, reward: 1.35523622755
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.3552362275458507, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.36)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: left, reward: 0.0376441781807
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 0.037644178180725185, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.04)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 1.0655899142
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.0655899142021907, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.07)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: -40.5355065425
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -40.535506542535934, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.54)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: left, reward: 2.15449635843
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 2.154496358431831, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.15)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: -0.203855553585
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': -0.20385555358456242, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded -0.20)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 0.831746260537
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 0.8317462605367798, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.83)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: 1.96815136603
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 1.9681513660291616, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 1.97)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.29002408535
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.2900240853527838, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.29)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: forward, reward: -10.3464215455
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 2, 't': 18, 'action': 'forward', 'reward': -10.346421545531195, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.35)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.62289227385
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.622892273854009, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.62)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 61
\-------------------------

Environment.reset(): Trial set up with start = (7, 2), destination = (5, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.4005; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 2.98589423778
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 2.9858942377812374, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.99)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: -4.53673254255
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 24, 't': 1, 'action': None, 'reward': -4.536732542550869, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.54)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: -5.47316245852
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': None, 'reward': -5.473162458517305, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -5.47)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 0.939991135073
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 0.9399911350730508, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.94)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: left, reward: 1.24216622893
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.2421662289273872, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.24)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: 0.989628274847
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.989628274846724, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.99)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: left, reward: -19.8478993605
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': -19.847899360472077, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.85)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 2.80123733004
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.8012373300443425, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.80)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 2.30850728556
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.3085072855603217, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.31)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 1.47256794647
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.472567946472573, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.47)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: right, reward: 1.55394364628
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.553943646277129, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 1.55)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: None, reward: 2.37926403646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 14, 't': 11, 'action': None, 'reward': 2.379264036464831, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.38)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: None, reward: 1.72407441054
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.7240744105391779, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.72)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 5), heading: (0, -1), action: left, reward: 1.9366957195
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 12, 't': 13, 'action': 'left', 'reward': 1.9366957195007184, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.94)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: left, reward: 1.85785337435
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 11, 't': 14, 'action': 'left', 'reward': 1.8578533743511565, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.86)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 62
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (7, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.3946; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3946; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: forward, reward: -9.9113675136
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': -9.911367513597911, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.91)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 1.50569220047
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.5056922004732676, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.51)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 1.46280015986
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.462800159862001, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.46)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: forward, reward: -9.9414752067
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': -9.941475206701382, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent attempted driving forward through a red light. (rewarded -9.94)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 2.44103053991
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.441030539910225, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.44)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: forward, reward: 0.187892642819
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 0.1878926428187231, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 0.19)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: right, reward: 0.756503069198
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.7565030691977099, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent drove right instead of left. (rewarded 0.76)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: forward, reward: 0.273663171584
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 0.27366317158442843, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove forward instead of right. (rewarded 0.27)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: right, reward: -20.6058370833
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': -20.605837083313098, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.61)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: forward, reward: -10.756941824
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': -10.756941823952607, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.76)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 0.923256345659
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': None, 'reward': 0.9232563456591782, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.92)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: 0.913936681162
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 0.913936681162441, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.91)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: 2.12415430289
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': 2.124154302885513, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.12)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: -4.63887254542
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 13, 'action': None, 'reward': -4.63887254542045, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.64)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: forward, reward: 1.53711962131
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': 1.537119621305067, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.54)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: forward, reward: -10.9984129233
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': -10.998412923299135, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -11.00)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: left, reward: -9.63033192217
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 4, 't': 16, 'action': 'left', 'reward': -9.630331922169281, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent attempted driving left through a red light. (rewarded -9.63)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: left, reward: 0.0550945746246
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 3, 't': 17, 'action': 'left', 'reward': 0.055094574624597326, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.06)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: forward, reward: 0.807200911753
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 2, 't': 18, 'action': 'forward', 'reward': 0.8072009117530934, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent drove forward instead of right. (rewarded 0.81)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: forward, reward: 0.379353694221
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': 0.37935369422089715, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', None, 'forward')
Agent drove forward instead of right. (rewarded 0.38)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 63
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (1, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.3887; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: forward, reward: -9.21571899905
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': -9.215718999052175, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.22)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: 2.02060861338
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.0206086133838923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.02)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: None, reward: 1.4103549413
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.410354941296204, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.41)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: left, reward: -10.1888352402
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -10.188835240235717, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.19)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: forward, reward: -10.0670320353
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': -10.06703203533611, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.07)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: forward, reward: 1.76837558436
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.768375584355805, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.77)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: right, reward: 1.7408366743
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.7408366743029668, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 1.74)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 1.64753933171
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.6475393317107587, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.65)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 1.95618680516
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.956186805157944, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.96)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: left, reward: -9.33765351854
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': -9.337653518538279, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -9.34)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: -5.78337127678
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': -5.783371276782044, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.78)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: left, reward: 1.59179079875
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.5917907987484536, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.59)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: right, reward: -0.320324756537
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': -0.32032475653651615, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded -0.32)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: None, reward: 0.67442751481
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 7, 't': 13, 'action': None, 'reward': 0.6744275148103058, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.67)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: left, reward: -10.0403088697
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': -10.040308869731305, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.04)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: left, reward: 1.22399908092
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.2239990809215848, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.22)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: left, reward: -9.02750494418
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': -9.027504944176462, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.03)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: 0.398427544345
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 3, 't': 17, 'action': 'left', 'reward': 0.3984275443453851, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 0.40)
10% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 64
\-------------------------

Environment.reset(): Trial set up with start = (2, 2), destination = (4, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.3829; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3829; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: forward, reward: -40.0503208243
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': -40.05032082426596, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.05)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: left, reward: -9.26150981345
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': -9.26150981345204, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.26)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: 2.17021899788
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.170218997882973, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.17)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: right, reward: 1.80725455241
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 1.8072545524062427, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 1.81)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: forward, reward: 1.61503689925
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.6150368992519089, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove forward instead of left. (rewarded 1.62)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: left, reward: -9.21013044974
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': -9.210130449736896, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.21)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: forward, reward: 0.750439668057
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 0.7504396680572892, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove forward instead of left. (rewarded 0.75)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 2.74384896808
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 2.7438489680835385, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.74)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: right, reward: -19.5954599077
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 17, 't': 8, 'action': 'right', 'reward': -19.59545990770418, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.60)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: forward, reward: 1.89754945046
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 1.8975494504612989, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.90)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 65
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (5, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.3772; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: forward, reward: 1.80566264971
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.805662649706121, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.81)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: left, reward: 0.144181454953
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 0.14418145495318757, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.14)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: left, reward: 1.46291099407
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.462910994065672, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent drove left instead of forward. (rewarded 1.46)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: right, reward: 2.78505219694
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 2.7850521969409527, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.79)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: right, reward: 1.20253490576
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.2025349057618715, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.20)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: 2.874787587
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.8747875869982114, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.87)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: 1.2796254812
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.2796254811998737, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.28)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: 1.00522301522
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.0052230152184998, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 1.01)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: forward, reward: 0.00267742870365
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 0.002677428703653839, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove forward instead of left. (rewarded 0.00)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 1.22509667582
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.2250966758179531, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.23)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 0.832470859272
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 0.8324708592722945, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.83)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: forward, reward: -9.4915279671
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': -9.491527967104238, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.49)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 1.26856137617
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.268561376172506, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.27)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: forward, reward: 0.444011369047
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 0.444011369046834, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.44)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: left, reward: 1.78869980327
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': 1.7886998032675572, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.79)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: left, reward: 0.718565580288
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 0.7185655802884179, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent followed the waypoint left. (rewarded 0.72)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 0.89015086032
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': None, 'reward': 0.8901508603195558, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.89)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.66008117473
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.6600811747251043, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.66)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 2.002264433
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 2, 't': 18, 'action': None, 'reward': 2.0022644329982944, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.00)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: -0.420927572603
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 1, 't': 19, 'action': 'right', 'reward': -0.42092757260288594, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'left', 'left')
Agent drove right instead of forward. (rewarded -0.42)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 66
\-------------------------

Environment.reset(): Trial set up with start = (6, 6), destination = (3, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.3716; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: left, reward: -20.8326919288
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'right'}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'forward', 'right'), 'deadline': 30, 't': 0, 'action': 'left', 'reward': -20.832691928799974, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'right')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.83)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 1.41953215983
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 29, 't': 1, 'action': 'forward', 'reward': 1.4195321598344992, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.42)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: left, reward: 1.14544166015
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 28, 't': 2, 'action': 'left', 'reward': 1.1454416601478754, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove left instead of forward. (rewarded 1.15)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: left, reward: -10.7156189344
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': 'left', 'reward': -10.715618934367356, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.72)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: right, reward: 1.11554596639
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 1.1155459663902787, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.12)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: right, reward: 0.293063424454
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.29306342445424616, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 0.29)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: None, reward: 2.0570039576
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 6, 'action': None, 'reward': 2.057003957598278, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.06)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: forward, reward: 1.00688578044
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 1.0068857804397324, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 1.01)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 1.90145910161
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.901459101605986, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.90)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: right, reward: -0.108169621524
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 21, 't': 9, 'action': 'right', 'reward': -0.10816962152434595, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded -0.11)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: None, reward: 2.32117195624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': 2.3211719562355477, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.32)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: forward, reward: -9.11965417418
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': -9.119654174182031, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.12)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: right, reward: 0.337992890093
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 0.3379928900933359, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 0.34)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 1.65980353826
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 17, 't': 13, 'action': None, 'reward': 1.6598035382572358, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.66)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 2.34822032849
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 2.348220328490269, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.35)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 1.04073690028
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.040736900284027, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.04)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 1.45989424502
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.4598942450206085, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.46)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: 0.724383700516
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 0.7243837005156331, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent followed the waypoint forward. (rewarded 0.72)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: -4.63332482608
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 12, 't': 18, 'action': None, 'reward': -4.633324826079626, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.63)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: -39.1127432913
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': -39.11274329125219, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.11)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 0.82158763686
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 10, 't': 20, 'action': None, 'reward': 0.8215876368604897, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.82)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 0.861836315262
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 21, 'action': None, 'reward': 0.8618363152622488, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.86)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: -0.0237952605793
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 8, 't': 22, 'action': 'forward', 'reward': -0.023795260579319022, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded -0.02)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: 1.11088162165
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 23, 'action': 'left', 'reward': 1.1108816216519524, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.11)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: None, reward: 1.54490781179
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 6, 't': 24, 'action': None, 'reward': 1.544907811792062, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.54)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: None, reward: -4.2273969222
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 5, 't': 25, 'action': None, 'reward': -4.2273969222025265, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.23)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: -0.570938945786
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 4, 't': 26, 'action': 'forward', 'reward': -0.5709389457857259, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded -0.57)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: left, reward: 0.334019825918
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 3, 't': 27, 'action': 'left', 'reward': 0.3340198259183407, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.33)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: forward, reward: -9.20087877258
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 2, 't': 28, 'action': 'forward', 'reward': -9.200878772576113, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -9.20)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: right, reward: 0.324905450862
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 1, 't': 29, 'action': 'right', 'reward': 0.3249054508624958, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 0.32)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 67
\-------------------------

Environment.reset(): Trial set up with start = (7, 6), destination = (4, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.3660; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3660; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: left, reward: 0.328843900647
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 0.32884390064672897, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 0.33)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: right, reward: 1.76125056813
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.7612505681278647, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.76)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: None, reward: 2.75484794922
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.754847949215048, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.75)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: None, reward: 1.43649524154
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.4364952415407184, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.44)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: right, reward: -0.0178874797009
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': -0.017887479700873343, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded -0.02)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: left, reward: -10.1457458962
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': -10.14574589623472, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.15)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: forward, reward: -39.5565300893
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': -39.55653008931339, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.56)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: left, reward: 1.01658978315
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.0165897831512969, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.02)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: None, reward: 2.09080530943
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.090805309430576, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.09)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: left, reward: -9.3430453966
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': -9.343045396595624, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.34)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: forward, reward: 1.28722946087
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 1.2872294608724888, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.29)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 0.854711767536
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 11, 'action': None, 'reward': 0.8547117675356655, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.85)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 1.74078193582
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.7407819358242873, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.74)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: left, reward: 1.24196127708
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.2419612770759707, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.24)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 68
\-------------------------

Environment.reset(): Trial set up with start = (8, 7), destination = (4, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.3606; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.77038535728
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.7703853572776778, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.77)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.7277163176
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.7277163176025727, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.73)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.13518421787
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.1351842178723333, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.14)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.24295755872
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.2429575587249486, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.24)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.77514785221
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.7751478522116093, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.78)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: 0.361223825002
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 0.36122382500165184, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 0.36)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: right, reward: 1.1601375576
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 1.1601375576017228, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.16)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: right, reward: -19.5226902112
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 18, 't': 7, 'action': 'right', 'reward': -19.52269021124449, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.52)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: right, reward: 0.22282501595
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 0.22282501595002258, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.22)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: right, reward: 1.07543963403
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 1.0754396340276957, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.08)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: None, reward: -5.0873717259
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': -5.087371725900831, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.09)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: left, reward: 1.23187060738
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 1.231870607381049, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.23)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: left, reward: 1.06662809843
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 1.066628098431969, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.07)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 0.861435072117
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 0.8614350721174826, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 0.86)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 2.29281503239
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 2.292815032394444, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.29)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: left, reward: 1.62323391512
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 10, 't': 15, 'action': 'left', 'reward': 1.6232339151208732, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.62)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: right, reward: 0.94833698704
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 0.948336987039982, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.95)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: forward, reward: 1.59466176583
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 8, 't': 17, 'action': 'forward', 'reward': 1.5946617658335018, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.59)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: -5.5302300384
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 7, 't': 18, 'action': None, 'reward': -5.5302300384020375, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.53)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: -0.330352721013
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 6, 't': 19, 'action': None, 'reward': -0.3303527210128717, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded -0.33)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: left, reward: -9.75372394913
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 5, 't': 20, 'action': 'left', 'reward': -9.75372394912626, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.75)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: forward, reward: -9.44917651296
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': -9.449176512962092, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.45)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 1.44022049676
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 3, 't': 22, 'action': 'right', 'reward': 1.4402204967581962, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.44)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: -5.27615546101
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 2, 't': 23, 'action': None, 'reward': -5.276155461005756, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.28)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: forward, reward: 0.748277699416
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 1, 't': 24, 'action': 'forward', 'reward': 0.7482776994155107, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.75)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 69
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (1, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.3552; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3552; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3552; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: 1.25191821166
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.2519182116594492, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 1.25)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: forward, reward: 1.93529924844
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.935299248441562, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove forward instead of left. (rewarded 1.94)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: right, reward: 0.969368803448
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.9693688034484652, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove right instead of left. (rewarded 0.97)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: right, reward: 1.68887704779
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.6888770477874355, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent drove right instead of forward. (rewarded 1.69)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: right, reward: 1.07495463758
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.0749546375800714, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove right instead of left. (rewarded 1.07)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 2.59157288636
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.5915728863552623, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.59)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: left, reward: 1.00037756027
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.0003775602688507, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 1.00)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: -5.25269995204
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': -5.252699952039669, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.25)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: right, reward: 1.99627216711
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.9962721671146515, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.00)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: 1.40382684488
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.403826844881234, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.40)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 1.33038626183
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 1.3303862618274305, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.33)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: -10.1342934795
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': -10.134293479474424, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.13)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 1.1432833798
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.1432833798008373, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.14)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: 1.1907327012
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.1907327011994633, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.19)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 70
\-------------------------

Environment.reset(): Trial set up with start = (2, 2), destination = (4, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.3499; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 1.25047505294
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.2504750529391844, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.25)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: left, reward: 1.7968036973
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.7968036972985568, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.80)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 1.61618219679
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.6161821967916183, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.62)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 1.46861272699
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.4686127269873963, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.47)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 1.46306675205
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.4630667520505427, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.46)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 2.45047068595
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.450470685949715, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.45)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 0.995212036429
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 14, 't': 6, 'action': None, 'reward': 0.9952120364291479, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.00)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: left, reward: 1.84869035813
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.8486903581341432, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.85)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 1.48837579692
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.488375796919586, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.49)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: 2.50246031907
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.5024603190729744, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.50)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: left, reward: 1.2762322321
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 1.276232232102073, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.28)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 71
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (5, 2), deadline = 30
Simulating trial. . . 
epsilon = 0.3447; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3447; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3447; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: 1.80988648723
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.809886487230201, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.81)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: forward, reward: -9.19496826724
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 29, 't': 1, 'action': 'forward', 'reward': -9.194968267238648, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -9.19)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: forward, reward: -39.8638912793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': -39.863891279303466, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.86)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: 2.55938073142
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 27, 't': 3, 'action': None, 'reward': 2.5593807314167627, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.56)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: forward, reward: -10.5797172766
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', 'right'), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': -10.57971727664354, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'right')
Agent attempted driving forward through a red light. (rewarded -10.58)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: right, reward: 0.859046799999
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.8590467999988377, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.86)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: right, reward: 2.92211929653
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 2.92211929652656, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.92)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: -40.4347574471
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 23, 't': 7, 'action': 'left', 'reward': -40.434757447077104, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.43)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: right, reward: 2.13688879242
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 2.1368887924201276, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.14)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.31514667515
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 21, 't': 9, 'action': None, 'reward': 2.3151466751527923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.32)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: 0.943506823132
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 0.9435068231320527, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.94)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: forward, reward: 1.15569006476
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': 1.1556900647639965, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.16)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: None, reward: 2.17373561268
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.1737356126771035, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.17)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 0.954653980012
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 0.9546539800115688, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.95)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: forward, reward: 1.7233142774
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 16, 't': 14, 'action': 'forward', 'reward': 1.7233142774011494, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.72)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: left, reward: 1.49348957525
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 15, 'action': 'left', 'reward': 1.4934895752490192, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.49)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: None, reward: 1.40043325353
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.4004332535320307, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.40)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: left, reward: 1.43101650378
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 17, 'action': 'left', 'reward': 1.4310165037835851, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.43)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: 2.19354944934
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 2.193549449338307, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.19)
37% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 72
\-------------------------

Environment.reset(): Trial set up with start = (3, 6), destination = (1, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.3396; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3396; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 1.66693246994
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.6669324699433166, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.67)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: right, reward: 2.4877245881
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 2.48772458810189, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.49)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: right, reward: 1.39330698327
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.3933069832726346, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.39)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: None, reward: -4.52491561507
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 22, 't': 3, 'action': None, 'reward': -4.5249156150742, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.52)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: right, reward: 1.30999927338
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 1.309999273382663, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.31)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: left, reward: 2.46557341408
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 2.465573414080283, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.47)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: 1.96505145321
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.9650514532065624, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.97)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: -40.400636225
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': -40.400636225027625, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.40)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: forward, reward: -10.2993656762
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': -10.299365676248446, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.30)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: forward, reward: 1.88214187181
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 1.882141871814863, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.88)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: forward, reward: 1.96745297666
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.9674529766632367, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.97)
56% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 73
\-------------------------

Environment.reset(): Trial set up with start = (7, 2), destination = (4, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.3345; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 1.45962839641
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.4596283964077805, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.46)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 2.06221007214
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.062210072138667, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.06)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 1.39651394656
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.3965139465595762, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.40)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 2.34055420048
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.3405542004839157, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.34)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: left, reward: 0.986053639373
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 0.9860536393725419, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.99)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: left, reward: -40.0493444915
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 20, 't': 5, 'action': 'left', 'reward': -40.04934449150314, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.05)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 1.58363146859
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 1.5836314685892692, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.58)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 1.85596030222
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 1.855960302215872, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.86)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 1.88103487493
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.8810348749302555, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.88)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: left, reward: 2.49219421853
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 2.49219421852981, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.49)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: None, reward: 1.487776159
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.4877761589993326, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.49)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: None, reward: 0.8447854202
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 14, 't': 11, 'action': None, 'reward': 0.8447854202000102, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 0.84)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: left, reward: -9.61416202573
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 12, 'action': 'left', 'reward': -9.61416202573006, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.61)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: forward, reward: 2.06012102596
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 2.060121025963362, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.06)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: forward, reward: -9.65959944748
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 11, 't': 14, 'action': 'forward', 'reward': -9.65959944748381, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.66)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: forward, reward: 1.37257378703
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 1.3725737870281072, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.37)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: left, reward: -9.19988053922
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 9, 't': 16, 'action': 'left', 'reward': -9.19988053921556, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.20)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: left, reward: -9.52462816845
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 17, 'action': 'left', 'reward': -9.524628168447027, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.52)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 0.769641538923
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 7, 't': 18, 'action': None, 'reward': 0.7696415389228666, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.77)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: forward, reward: -9.81162900111
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': -9.811629001113088, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.81)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 0.561051940856
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 5, 't': 20, 'action': None, 'reward': 0.5610519408557084, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.56)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: 1.25457181797
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': 1.254571817973039, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.25)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: left, reward: -40.5839301174
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 3, 't': 22, 'action': 'left', 'reward': -40.58393011742167, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.58)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: -39.7278632496
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 2, 't': 23, 'action': 'forward', 'reward': -39.72786324959015, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.73)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: 1.21508177302
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 24, 'action': None, 'reward': 1.2150817730205978, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.22)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 74
\-------------------------

Environment.reset(): Trial set up with start = (4, 4), destination = (3, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.3296; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3296; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: left, reward: 2.39665445739
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.3966544573924438, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.40)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: left, reward: 1.33434151307
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.3343415130659395, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.33)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.36196958759
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.36196958759114, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.36)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 0.291043651002
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.29104365100175633, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.29)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: left, reward: 2.77021240652
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 2.770212406516956, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.77)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: forward, reward: -0.08523499138
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': -0.08523499138001922, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent drove forward instead of left. (rewarded -0.09)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: right, reward: 1.46335466905
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.4633546690519927, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.46)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 0.0584414686608
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': 0.058441468660823004, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 0.06)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: right, reward: 1.68195491359
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.681954913585225, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.68)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: right, reward: 1.74575467698
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.7457546769817243, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.75)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: forward, reward: -10.7241305714
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': -10.724130571406413, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -10.72)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: right, reward: 1.69471830925
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.6947183092453446, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.69)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: None, reward: 1.20296841398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.202968413984787, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.20)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: left, reward: 1.33988796208
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.3398879620841238, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.34)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: left, reward: 2.43556413803
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': 2.435564138027202, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.44)
25% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 75
\-------------------------

Environment.reset(): Trial set up with start = (1, 7), destination = (5, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.3247; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.84871566346
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.8487156634589383, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.85)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 0.559343686578
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 0.5593436865777919, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.56)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 2.63344525658
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.633445256579229, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.63)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 2.3309462219
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.3309462219005828, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.33)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 0.747994088902
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 0.7479940889018254, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.75)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: left, reward: -10.2338471806
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': -10.233847180562554, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.23)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 1.03331646834
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.0333164683405143, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.03)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: -5.9885455989
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 18, 't': 7, 'action': None, 'reward': -5.988545598900259, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -5.99)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 0.723273188697
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 0.7232731886966582, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.72)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: left, reward: 2.60792983345
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 2.6079298334527152, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.61)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: forward, reward: 1.40218520381
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.4021852038129599, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.40)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: forward, reward: -40.6253018895
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': -40.62530188947408, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.63)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 1.41683440142
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.4168344014218306, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.42)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: forward, reward: 2.58086177674
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 2.580861776742995, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.58)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: 1.64619190656
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 1.6461919065560617, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.65)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 76
\-------------------------

Environment.reset(): Trial set up with start = (8, 2), destination = (7, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.3198; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3198; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: forward, reward: 0.973351944395
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 0.9733519443952803, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.97)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 2.67774342371
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'right'), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.677743423710282, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 2.68)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: right, reward: 0.30717514183
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.3071751418297203, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.31)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 0.730615704622
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.73061570462197, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.73)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: forward, reward: 0.194259128007
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'right'), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 0.19425912800650347, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'right')
Agent drove forward instead of right. (rewarded 0.19)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: forward, reward: -10.8237991722
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': -10.823799172215725, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.82)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 1.68304257997
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.6830425799733493, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.68)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.65098692383
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.650986923831814, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.65)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.28146907663
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.281469076625857, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.28)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: 2.1578675701
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.1578675700991816, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.16)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: 2.49811742655
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.498117426550526, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.50)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 1.80956860432
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.8095686043181571, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.81)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 2.17397347142
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': 2.173973471415027, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.17)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: -4.37121624104
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 7, 't': 13, 'action': None, 'reward': -4.3712162410360484, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.37)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: right, reward: 0.104092070296
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 0.10409207029574474, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.10)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 0.700422031457
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 0.7004220314570446, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.70)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: left, reward: 2.27734119985
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 2.2773411998490545, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.28)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 0.767322699444
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 3, 't': 17, 'action': None, 'reward': 0.7673226994436524, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.77)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 1.4506908733
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.4506908732963908, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.45)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 1.28555128805
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.2855512880464015, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.29)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 77
\-------------------------

Environment.reset(): Trial set up with start = (6, 3), destination = (4, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.3151; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3151; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3151; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 2.99412166416
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.994121664162976, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.99)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 1.63521774458
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.6352177445799954, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.64)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: left, reward: -10.6059356623
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': -10.605935662280583, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.61)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 2.63740042504
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.6374004250423546, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.64)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 1.39440334472
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.3944033447191952, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.39)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 0.913653892295
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 0.9136538922946784, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.91)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: 1.20706838937
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.2070683893683407, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.21)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: -4.90119202882
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 13, 't': 7, 'action': None, 'reward': -4.901192028824525, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.90)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: -5.22230052065
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': -5.222300520646882, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.22)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: left, reward: 1.3559622145
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.3559622144965549, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.36)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: left, reward: -10.3830120291
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': -10.383012029138897, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent attempted driving left through a red light. (rewarded -10.38)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 0.280399588893
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.28039958889271466, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.28)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: -4.07680415064
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': -4.076804150640535, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.08)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: forward, reward: -40.7243368412
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': -40.724336841171315, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.72)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 1.11572235828
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'forward'), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.1157223582840794, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.12)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 2.19189333645
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.191893336445313, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.19)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 1.58075056513
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 16, 'action': None, 'reward': 1.580750565128986, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.58)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: left, reward: 0.891791801207
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'left', 'reward': 0.891791801207114, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.89)
10% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 78
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (7, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.3104; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: None, reward: -4.59589333593
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': -4.595893335930365, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.60)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 2.25323024433
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.253230244325854, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.25)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 0.996108123457
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.996108123457229, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent drove right instead of forward. (rewarded 1.00)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.89846990806
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.898469908056157, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.90)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.44128973399
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.441289733990807, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.44)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: left, reward: 2.30069090908
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.300690909077831, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.30)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: forward, reward: 2.30352370592
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.3035237059151874, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.30)
65% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 79
\-------------------------

Environment.reset(): Trial set up with start = (7, 7), destination = (4, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.3057; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3057; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3057; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3057; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 2.35708040612
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'right'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.3570804061194055, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'right')
Agent properly idled at a red light. (rewarded 2.36)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 1.99062409683
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.990624096828701, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.99)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 2.24675172839
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.2467517283891225, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.25)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 2.60058548784
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.6005854878385213, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.60)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 2.75211575645
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.75211575644722, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.75)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 1.13854589191
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.138545891907148, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.14)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: forward, reward: 2.4216815945
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.4216815944988177, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.42)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: forward, reward: 1.11133443343
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.1113344334273652, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.11)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 1.77605474377
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.7760547437726675, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.78)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: forward, reward: 2.03255051288
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.0325505128821906, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.03)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: right, reward: 1.4280543969
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.4280543968953336, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent followed the waypoint right. (rewarded 1.43)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 80
\-------------------------

Environment.reset(): Trial set up with start = (6, 2), destination = (1, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.3012; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3012; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3012; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3012; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.3012; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: right, reward: 1.02617105741
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.0261710574058864, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.03)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 1.06571113334
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.065711133336765, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.07)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 2.87643121982
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.8764312198248096, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.88)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 1.31681266567
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.3168126656716337, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.32)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 2.32421989415
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.324219894148288, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.32)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: -0.00463399479567
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': -0.004633994795673058, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded -0.00)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: None, reward: 2.04755655903
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.047556559034484, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.05)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: None, reward: 1.5007330505
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.5007330504984167, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.50)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: None, reward: 1.50048511052
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.5004851105215071, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.50)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: 1.85724702058
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.8572470205798193, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.86)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: left, reward: 2.01955710631
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.0195571063077677, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.02)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: left, reward: -9.89424606916
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': -9.894246069158966, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.89)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: 1.25851558522
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'forward'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.2585155852178642, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.26)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: forward, reward: 0.689717066642
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 0.6897170666419108, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.69)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 81
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (7, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.2967; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2967; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: forward, reward: 1.69273449116
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'right'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 1.6927344911632773, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'right')
Agent drove forward instead of left. (rewarded 1.69)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 1.69542745925
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.6954274592510872, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.70)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.11567698704
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.115676987043506, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.12)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.23424722514
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.23424722514382, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.23)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: 1.17319685255
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 1.1731968525451477, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 1.17)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: right, reward: 1.74956668604
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 1.7495666860421424, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.75)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 1.98175335131
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 1.9817533513073256, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.98)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: forward, reward: 1.14706541427
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.1470654142690628, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.15)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 0.492408066732
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'forward'), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 0.4924080667317755, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'forward')
Agent drove right instead of forward. (rewarded 0.49)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: left, reward: 1.72779934993
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 1.7277993499261164, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.73)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: forward, reward: 1.01753674301
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.0175367430052207, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent drove forward instead of right. (rewarded 1.02)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 1.10209840106
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.102098401060753, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.10)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: 0.910257363025
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 0.9102573630250768, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.91)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: 1.16171569338
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'left', 'reward': 1.1617156933774435, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.16)
44% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 82
\-------------------------

Environment.reset(): Trial set up with start = (1, 7), destination = (5, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.2923; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 1.30961814568
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.3096181456838165, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent drove right instead of forward. (rewarded 1.31)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 1.68273073649
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.6827307364871673, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.68)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 1.35200978325
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.3520097832462905, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.35)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: forward, reward: -10.0744840874
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': -10.074484087442789, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.07)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: None, reward: 1.51584235279
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.5158423527923859, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.52)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 1.67314353122
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.6731435312186933, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 1.67)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 2.63638214225
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.636382142253095, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.64)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 1.67475941867
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.6747594186661097, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.67)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: forward, reward: 2.14811912231
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 2.1481191223143927, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.15)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: forward, reward: 2.18855935249
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.1885593524899702, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.19)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: right, reward: 1.49843547798
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.498435477983018, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 1.50)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 83
\-------------------------

Environment.reset(): Trial set up with start = (1, 4), destination = (3, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.2879; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2879; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2879; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2879; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: right, reward: 1.9032216062
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.903221606197991, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.90)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: left, reward: 1.51722420896
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.517224208963634, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.52)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: forward, reward: 1.60282382752
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 1.6028238275236413, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.60)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: left, reward: 1.77156549655
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.7715654965476886, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.77)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: None, reward: 1.38841986545
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.3884198654481241, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.39)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: right, reward: 1.16483304819
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.1648330481944507, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.16)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: -4.63981000313
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': None, 'reward': -4.639810003127931, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.64)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: right, reward: 0.897520614563
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.8975206145631032, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.90)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: right, reward: 1.17751250381
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.1775125038100815, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.18)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: left, reward: 2.01264023621
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.012640236207595, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.01)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 84
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (6, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.2837; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: None, reward: 1.0534672275
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.0534672275039476, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.05)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: right, reward: 1.32727044107
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.3272704410693037, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.33)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: right, reward: 1.32986278083
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.3298627808289147, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.33)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: right, reward: 1.52802076327
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 1.5280207632710723, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove right instead of left. (rewarded 1.53)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: forward, reward: 1.50051913292
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 1.5005191329218752, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.50)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: left, reward: 0.47045654937
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 25, 't': 5, 'action': 'left', 'reward': 0.47045654936967074, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.47)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 1.59031481835
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.5903148183505802, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.59)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 1.09412785533
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.094127855331662, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.09)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 2.3235720085
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.3235720085005296, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.32)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: forward, reward: 2.02930244635
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 2.029302446347081, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent followed the waypoint forward. (rewarded 2.03)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: left, reward: -19.3209542781
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': -19.320954278134742, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.32)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: left, reward: 1.55135301482
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 11, 'action': 'left', 'reward': 1.551353014817596, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.55)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 85
\-------------------------

Environment.reset(): Trial set up with start = (1, 4), destination = (4, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.2794; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2794; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2794; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2794; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.58233638307
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.5823363830740824, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.58)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.49586526968
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.4958652696802313, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.50)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.40057804168
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.400578041681634, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.40)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.55442814593
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.5544281459265143, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.55)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.25248565296
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.2524856529612427, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.25)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: -4.2380637779
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 20, 't': 5, 'action': None, 'reward': -4.238063777897564, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.24)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: left, reward: 1.12744285146
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.1274428514608328, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent drove left instead of forward. (rewarded 1.13)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: None, reward: 1.54508575108
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.545085751083456, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.55)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: forward, reward: -10.8879642488
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': -10.88796424877654, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.89)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: right, reward: 1.74838284157
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 1.7483828415682272, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.75)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: 1.71488491691
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.7148849169054357, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.71)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: left, reward: 1.36180894538
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 1.3618089453798716, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.36)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: right, reward: 0.829879357471
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 0.8298793574710499, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.83)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: 1.46707443145
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 1.4670744314545232, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.47)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: left, reward: 2.44968788278
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 11, 't': 14, 'action': 'left', 'reward': 2.4496878827754016, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.45)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: -5.19098764731
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 10, 't': 15, 'action': None, 'reward': -5.190987647312627, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.19)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: forward, reward: 2.12379934536
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 2.123799345356441, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.12)
32% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 86
\-------------------------

Environment.reset(): Trial set up with start = (3, 3), destination = (7, 4), deadline = 25
Simulating trial. . . 
epsilon = 0.2753; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: right, reward: 1.50788013905
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.5078801390519827, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.51)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: right, reward: 1.58441914677
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.5844191467732602, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.58)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: None, reward: 2.53851917805
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.538519178045626, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.54)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: right, reward: 0.226876869002
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 0.22687686900240456, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.23)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: right, reward: 1.78485750495
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 1.7848575049519564, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.78)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: None, reward: 1.60009920367
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.6000992036678672, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.60)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: right, reward: 2.35910660416
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 2.3591066041590896, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.36)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: right, reward: 0.402767467751
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 0.40276746775102246, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.40)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: left, reward: 1.94977490223
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 17, 't': 8, 'action': 'left', 'reward': 1.949774902228, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.95)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: right, reward: 0.383214330191
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'forward'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 0.3832143301908535, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'forward')
Agent drove right instead of forward. (rewarded 0.38)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: left, reward: 1.26568394754
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 1.265683947541899, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.27)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 0.853241017684
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 14, 't': 11, 'action': None, 'reward': 0.8532410176837999, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.85)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 1.7531624084
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 1.753162408396291, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 1.75)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 2.18792361046
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 13, 'action': None, 'reward': 2.1879236104584514, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.19)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 1.73071097913
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.7307109791271635, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.73)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 1.53299617081
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 10, 't': 15, 'action': None, 'reward': 1.5329961708056596, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.53)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: 0.854941050702
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'left', 'reward': 0.8549410507023947, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.85)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: -10.4579080023
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 8, 't': 17, 'action': 'left', 'reward': -10.457908002323935, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent attempted driving left through a red light. (rewarded -10.46)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 1.09391292082
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.0939129208169887, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.09)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: right, reward: 1.65029635604
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 6, 't': 19, 'action': 'right', 'reward': 1.6502963560377693, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.65)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: right, reward: 1.05794715926
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 5, 't': 20, 'action': 'right', 'reward': 1.0579471592552854, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.06)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: left, reward: 0.435477202527
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 21, 'action': 'left', 'reward': 0.4354772025273035, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.44)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: -0.418113272111
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 3, 't': 22, 'action': 'forward', 'reward': -0.4181132721111305, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded -0.42)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 2.04464669067
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 2, 't': 23, 'action': None, 'reward': 2.0446466906661236, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.04)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 1.42804099937
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 1, 't': 24, 'action': None, 'reward': 1.4280409993693068, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.43)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 87
\-------------------------

Environment.reset(): Trial set up with start = (3, 2), destination = (5, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.2712; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: forward, reward: 1.04086158712
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.0408615871176887, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove forward instead of right. (rewarded 1.04)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: right, reward: 1.14034072592
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.1403407259164888, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.14)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: -4.71651902601
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': -4.7165190260118885, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.72)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 2.81987714508
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.8198771450812936, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.82)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 1.1482340996
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.1482340995973934, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.15)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: forward, reward: 2.74462383999
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.7446238399926512, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.74)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: None, reward: 1.44988286855
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.4498828685509064, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.45)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: None, reward: 1.51964546511
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.5196454651123117, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.52)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: forward, reward: -40.2093256495
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': -40.20932564945706, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.21)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: left, reward: 1.63430645896
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.634306458961359, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.63)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 88
\-------------------------

Environment.reset(): Trial set up with start = (7, 4), destination = (6, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.2671; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2671; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2671; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2671; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2671; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: None, reward: 2.35985831612
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'right'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.359858316123117, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 2.36)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: 1.65902007218
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.6590200721800863, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.66)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: left, reward: 2.23681909473
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 2.236819094732836, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent followed the waypoint left. (rewarded 2.24)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: left, reward: 2.38196807632
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 2.381968076315988, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.38)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 1.82238768948
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.8223876894820137, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.82)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 2.36392056699
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.363920566993503, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.36)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: None, reward: 0.0134473521469
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 14, 't': 6, 'action': None, 'reward': 0.01344735214692827, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.01)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: None, reward: 1.05776743575
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.0577674357524005, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.06)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: None, reward: 1.0066247164
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.0066247163952435, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.01)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 2.2576243328
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 2.25762433280071, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.26)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: right, reward: -0.0814162311905
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': -0.08141623119050989, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent drove right instead of forward. (rewarded -0.08)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 2.58104456203
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.5810445620286, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.58)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: forward, reward: -39.9971521619
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': -39.99715216189791, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.00)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: left, reward: 1.07491589714
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.0749158971399824, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.07)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: None, reward: 2.31334468957
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 2.313344689566052, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.31)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: None, reward: 1.1216468754
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.1216468754012636, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.12)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: left, reward: 0.603599792884
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 0.6035997928840895, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.60)
15% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 89
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (7, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.2632; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: forward, reward: 0.311534505057
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': 0.31153450505655855, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.31)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: None, reward: 2.1464266769
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 29, 't': 1, 'action': None, 'reward': 2.1464266769028306, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.15)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: None, reward: 2.89040721587
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 28, 't': 2, 'action': None, 'reward': 2.890407215872508, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.89)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: None, reward: 1.47743425931
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.4774342593052137, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.48)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: right, reward: 1.04984923233
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 1.0498492323250126, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 1.05)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: 1.82966205775
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 5, 'action': None, 'reward': 1.8296620577520557, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.83)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: -10.81768726
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 24, 't': 6, 'action': 'left', 'reward': -10.817687260036376, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent attempted driving left through a red light. (rewarded -10.82)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: 1.00262296229
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.0026229622870169, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: 2.19323364113
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.193233641127529, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.19)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: -5.39245680325
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 21, 't': 9, 'action': None, 'reward': -5.392456803246786, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.39)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: left, reward: 1.72197957336
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': 1.7219795733597876, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.72)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: left, reward: 1.52163310579
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 11, 'action': 'left', 'reward': 1.5216331057894839, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.52)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 1.19097774
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.1909777400030832, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.19)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 2.3108331332
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 17, 't': 13, 'action': None, 'reward': 2.3108331331962546, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 2.31)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: right, reward: 1.34467654465
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 1.3446765446536895, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.34)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: None, reward: 2.75518263348
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 15, 't': 15, 'action': None, 'reward': 2.755182633483254, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 2.76)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: left, reward: -9.50008121498
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': -9.500081214980778, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -9.50)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: forward, reward: 0.408945500064
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 0.4089455000642126, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove forward instead of left. (rewarded 0.41)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: None, reward: 2.3965372982
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 18, 'action': None, 'reward': 2.396537298199023, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.40)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: right, reward: -0.180132857166
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 11, 't': 19, 'action': 'right', 'reward': -0.18013285716582417, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded -0.18)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: right, reward: 1.41018783576
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 10, 't': 20, 'action': 'right', 'reward': 1.4101878357616868, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.41)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: left, reward: -40.9758740384
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 9, 't': 21, 'action': 'left', 'reward': -40.97587403843077, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.98)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: right, reward: 2.4480872666
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 8, 't': 22, 'action': 'right', 'reward': 2.4480872665985696, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.45)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: forward, reward: 0.650190654981
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 23, 'action': 'forward', 'reward': 0.6501906549814251, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.65)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: -5.96297977469
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 6, 't': 24, 'action': None, 'reward': -5.962979774686332, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.96)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: forward, reward: -9.69438270664
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 25, 'action': 'forward', 'reward': -9.694382706644538, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.69)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 0.312136646619
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 4, 't': 26, 'action': 'right', 'reward': 0.3121366466186615, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.31)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: forward, reward: -10.8700286541
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 3, 't': 27, 'action': 'forward', 'reward': -10.870028654085454, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.87)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: forward, reward: -10.2849194308
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 2, 't': 28, 'action': 'forward', 'reward': -10.284919430797295, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.28)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 0.130555503568
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 1, 't': 29, 'action': 'left', 'reward': 0.13055550356809364, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.13)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 90
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (4, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.2592; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2592; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2592; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2592; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2592; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: right, reward: 0.586408618255
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 0.5864086182553303, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove right instead of left. (rewarded 0.59)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: left, reward: -10.8901475434
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': -10.890147543402048, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.89)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: right, reward: 2.66470514504
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 2.6647051450447927, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.66)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 1.16602105514
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.1660210551423675, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.17)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: right, reward: 0.72600047363
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 0.726000473630099, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.73)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: None, reward: 1.77020829484
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.7702082948362485, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.77)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: None, reward: -4.87459378619
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': None, 'reward': -4.874593786192444, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.87)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: forward, reward: 0.660487445871
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 0.6604874458707519, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 0.66)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: 2.7251964215
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.725196421499721, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.73)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: -39.1185052143
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 9, 'action': 'left', 'reward': -39.118505214347216, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.12)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: left, reward: 0.948819477752
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 0.9488194777521528, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.95)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 0.0526758117826
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 0.05267581178263636, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.05)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: left, reward: 0.919530099587
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 0.9195300995868272, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.92)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 91
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (4, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.2554; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2554; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2554; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2554; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: left, reward: 1.86923974631
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'left', 'reward': 1.8692397463077608, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.87)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: forward, reward: 2.50742413145
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': 2.5074241314487757, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.51)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: forward, reward: 2.82659462511
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': 2.826594625110697, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.83)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: left, reward: 1.23765974397
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 1.2376597439740669, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.24)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: None, reward: 2.67550711602
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.6755071160192805, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.68)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (0, 1), action: None, reward: 2.8375252783
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.837525278297254, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.84)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: forward, reward: 2.30799448311
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.307994483111746, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.31)
72% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 92
\-------------------------

Environment.reset(): Trial set up with start = (6, 7), destination = (8, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.2516; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: left, reward: 1.28972127863
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 1.2897212786253036, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.29)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: left, reward: -9.82624976488
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'left', 'reward': -9.826249764879176, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.83)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 2.9048259376
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.904825937601472, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.90)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: None, reward: 2.78549172036
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.7854917203569602, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.79)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: forward, reward: 1.51629084919
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.516290849185737, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.52)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: left, reward: 2.87802345106
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.8780234510622167, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.88)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 93
\-------------------------

Environment.reset(): Trial set up with start = (7, 6), destination = (4, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.2478; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: forward, reward: 0.688077696502
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'right'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 0.6880776965015438, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'right')
Agent drove forward instead of right. (rewarded 0.69)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: forward, reward: 2.11993073488
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': 2.1199307348837397, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.12)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: right, reward: 1.00353205588
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'forward'), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.0035320558835605, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'forward')
Agent drove right instead of forward. (rewarded 1.00)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: -20.5071178761
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': -20.507117876078723, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.51)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: left, reward: 2.41935985846
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 2.4193598584630767, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.42)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: right, reward: 0.416924385669
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.4169243856686612, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.42)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: left, reward: 2.04141430097
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 2.041414300967594, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.04)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 1.16410822221
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.1641082222112087, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.16)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 2.70641785505
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.7064178550480573, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.71)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 1.65200605425
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.6520060542487895, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.65)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 1.59460408704
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.5946040870449438, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.59)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: -4.81587186556
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 14, 't': 11, 'action': None, 'reward': -4.815871865560572, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.82)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: 1.35457523749
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 1.3545752374891755, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.35)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 94
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (8, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.2441; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: forward, reward: 1.616064087
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 1.6160640870007348, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove forward instead of left. (rewarded 1.62)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: left, reward: 0.996680634376
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': 0.9966806343761803, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.00)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: left, reward: 1.37675342077
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 23, 't': 2, 'action': 'left', 'reward': 1.37675342076905, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.38)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 1.46715340816
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.4671534081633129, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.47)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 1.69848125689
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.6984812568937757, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.70)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: right, reward: 1.89708691006
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 1.8970869100627823, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 1.90)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: forward, reward: -0.0509544910394
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': -0.05095449103936456, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove forward instead of left. (rewarded -0.05)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: left, reward: 2.33021291226
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 2.330212912261728, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.33)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.63707898327
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.6370789832701378, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.64)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 0.326726996331
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 0.32672699633100777, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.33)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: left, reward: 0.973083010937
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 0.9730830109366786, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.97)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 1.66363180648
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.6636318064818063, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.66)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: forward, reward: 0.521739959635
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 0.5217399596345584, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 0.52)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: left, reward: -10.1543044965
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 13, 'action': 'left', 'reward': -10.15430449646319, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.15)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 1.45321404383
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.4532140438348538, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.45)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 0.705588103411
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 10, 't': 15, 'action': None, 'reward': 0.705588103410637, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.71)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: 2.4388473426
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 2.438847342600697, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.44)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 2.01829988761
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 8, 't': 17, 'action': None, 'reward': 2.018299887613391, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.02)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 1.27639060938
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.2763906093785957, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.28)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: -9.74729446929
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': -9.747294469287691, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.75)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 0.943878917593
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 5, 't': 20, 'action': None, 'reward': 0.9438789175928826, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.94)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: -4.81162142731
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 21, 'action': None, 'reward': -4.811621427314665, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.81)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: forward, reward: 1.75974170181
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 3, 't': 22, 'action': 'forward', 'reward': 1.759741701807835, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.76)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 0.267761509677
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 2, 't': 23, 'action': None, 'reward': 0.26776150967652157, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.27)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 0.42654651533
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 1, 't': 24, 'action': None, 'reward': 0.426546515330227, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.43)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 95
\-------------------------

Environment.reset(): Trial set up with start = (2, 7), destination = (6, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.2405; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: left, reward: 1.26057585734
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 25, 't': 0, 'action': 'left', 'reward': 1.2605758573388541, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.26)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: forward, reward: -10.9276928821
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': -10.92769288213071, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.93)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: left, reward: -9.59830845463
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': 'left', 'reward': -9.598308454631617, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.60)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: left, reward: 1.32722716889
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 1.3272271688858324, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.33)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 1.83643801385
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 1.836438013850239, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.84)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: forward, reward: 0.677492588672
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 0.677492588671713, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.68)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: left, reward: 1.0915845125
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.0915845125002288, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.09)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.58562159646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.5856215964558615, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.59)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: left, reward: -39.7828589546
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', 'right', 'forward'), 'deadline': 17, 't': 8, 'action': 'left', 'reward': -39.78285895464567, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.78)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.01238680007
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.0123868000686786, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.01)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.98023090875
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.9802309087465721, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.98)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: forward, reward: 1.37114647726
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.3711464772551336, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.37)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: forward, reward: 1.69129763961
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 1.6912976396075716, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.69)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: forward, reward: -39.2738015734
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': -39.27380157343777, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.27)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 2.18585683536
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 11, 't': 14, 'action': None, 'reward': 2.1858568353625527, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 2.19)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: right, reward: 0.902803216283
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 0.9028032162833046, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.90)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: forward, reward: 2.32557156561
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 2.3255715656081923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.33)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: 2.26552248434
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 17, 'action': None, 'reward': 2.2655224843409276, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.27)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: -10.5499769709
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 18, 'action': 'left', 'reward': -10.54997697093982, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.55)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: right, reward: -0.493080100241
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 6, 't': 19, 'action': 'right', 'reward': -0.49308010024075155, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded -0.49)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 0.939334726658
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 20, 'action': None, 'reward': 0.9393347266582002, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.94)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 1.52177706318
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 4, 't': 21, 'action': None, 'reward': 1.5217770631826266, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.52)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 0.336644314069
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 3, 't': 22, 'action': 'forward', 'reward': 0.33664431406891215, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.34)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: left, reward: 0.715389476973
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 2, 't': 23, 'action': 'left', 'reward': 0.7153894769732807, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 0.72)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: right, reward: -0.667690744387
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 1, 't': 24, 'action': 'right', 'reward': -0.6676907443868243, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove right instead of left. (rewarded -0.67)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 96
\-------------------------

Environment.reset(): Trial set up with start = (6, 2), destination = (8, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.2369; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: forward, reward: 0.843563042305
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 0.8435630423049296, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove forward instead of left. (rewarded 0.84)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: 1.81870209165
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.8187020916462187, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.82)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: 1.15366453178
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.1536645317762395, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.15)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: forward, reward: 0.00306348677408
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 0.0030634867740829685, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.00)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 2.55676096991
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.556760969905846, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.56)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 1.39236785793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.3923678579270005, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.39)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 2.06602990426
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.0660299042630976, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.07)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: forward, reward: 1.92196155323
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.9219615532300307, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.92)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 2.38167031298
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.381670312978257, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.38)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: forward, reward: 2.37900272095
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.379002720948234, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.38)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 0.356729208424
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 0.35672920842364897, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.36)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 2.49546838901
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 2.4954683890123137, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.50)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: -20.8091428162
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 8, 't': 12, 'action': 'right', 'reward': -20.80914281618701, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.81)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: left, reward: 0.690029218311
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 0.6900292183111145, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.69)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: right, reward: 1.22713085952
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.2271308595235566, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.23)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 1.77597005357
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.7759700535724474, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.78)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 0.997388715021
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.9973887150214942, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 1.00)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: None, reward: 0.572927693882
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 3, 't': 17, 'action': None, 'reward': 0.5729276938824756, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 0.57)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: right, reward: 1.2901487916
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 1.2901487915997885, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.29)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 1.93872092789
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 1.9387209278904394, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.94)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 97
\-------------------------

Environment.reset(): Trial set up with start = (1, 4), destination = (3, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.2334; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2334; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 2.73606442817
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.736064428169815, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.2060914731
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.2060914731037913, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.21)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.14160619482
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.141606194820293, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.14)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 2.40648834133
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.4064883413324116, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.41)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 2.94866068633
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.948660686325197, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.95)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: 2.74724588826
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 2.747245888259922, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.75)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: forward, reward: 2.00383124705
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.003831247051362, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent followed the waypoint forward. (rewarded 2.00)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: forward, reward: -0.0399255544992
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': -0.0399255544991568, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded -0.04)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: left, reward: 2.52134049704
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 8, 'action': 'left', 'reward': 2.5213404970383526, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.52)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: right, reward: 0.290018758168
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 0.2900187581679534, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove right instead of left. (rewarded 0.29)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: left, reward: 1.38777995258
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 1.3877799525758467, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.39)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: forward, reward: 0.875754793993
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 0.8757547939926663, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 0.88)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: left, reward: 2.60858609557
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 2.608586095568172, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.61)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: forward, reward: 1.50147042906
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 1.5014704290588383, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.50)
44% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 98
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (2, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.2299; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: right, reward: 0.265754982735
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'left'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 0.265754982734987, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'left')
Agent drove right instead of forward. (rewarded 0.27)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: right, reward: 0.510555274356
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.5105552743560325, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.51)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: left, reward: 2.69351272462
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 2.6935127246238935, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.69)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: left, reward: 1.98339946807
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.9833994680717009, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.98)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 1.69604687933
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.6960468793330636, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.70)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 0.372890063132
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 0.37289006313232775, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 0.37)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: right, reward: 0.453851926389
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.45385192638903504, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.45)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: left, reward: -9.49615200624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': -9.496152006242044, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent attempted driving left through a red light. (rewarded -9.50)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: 1.71819173837
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.7181917383686351, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.72)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 1.78799233395
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.787992333953591, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.79)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 1.77436422381
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.774364223812862, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.77)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 2.43451423006
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.4345142300574802, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.43)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 1.2349677435
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.2349677434954711, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.23)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: 1.75778669793
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.7577866979329455, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.76)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 1.80979725624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.8097972562370213, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.81)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: forward, reward: 1.61897437386
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': 1.618974373858505, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.62)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 99
\-------------------------

Environment.reset(): Trial set up with start = (3, 7), destination = (7, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.2265; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: forward, reward: -9.84579151552
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': -9.845791515520819, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.85)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: None, reward: 0.952994240719
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 19, 't': 1, 'action': None, 'reward': 0.9529942407191253, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 0.95)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: right, reward: 2.80751484433
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.807514844330221, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.81)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: None, reward: 2.9436481594
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.943648159399932, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.94)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: None, reward: 1.71149859771
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.7114985977088621, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.71)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: forward, reward: 1.936784146
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.936784145995397, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.94)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 2.19296028975
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.192960289753131, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.19)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 1.86745592295
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.8674559229452834, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.87)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 1.26845123557
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.268451235571995, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.27)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: 1.88772124716
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.8877212471596057, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.89)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 100
\-------------------------

Environment.reset(): Trial set up with start = (1, 3), destination = (5, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.2231; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: right, reward: 1.23595566125
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.2359556612463987, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 1.24)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: forward, reward: 2.14033394986
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 2.1403339498587304, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.14)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 1.7208110348
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.720811034802772, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.72)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: right, reward: -0.0417973476068
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': -0.0417973476068495, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded -0.04)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: right, reward: 0.682374827502
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.6823748275020906, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.68)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: right, reward: 1.74112829408
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.741128294078607, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.74)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: None, reward: 0.351193957004
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': None, 'reward': 0.35119395700390577, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.35)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: left, reward: 0.473234091786
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 0.47323409178588105, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.47)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.46703810623
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.467038106226428, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.47)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 1.86114486353
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.8611448635284136, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.86)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: forward, reward: 0.961685619897
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 0.961685619897237, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.96)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: 2.68061289897
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 2.6806128989738163, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.68)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 2.59576751976
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 2.5957675197615577, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.60)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: None, reward: 1.92000232938
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.9200023293843351, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.92)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: None, reward: 2.16616406451
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 2.166164064513518, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.17)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: None, reward: 1.43530101923
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.4353010192304494, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.44)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: forward, reward: 0.683001079214
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 0.6830010792141159, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.68)
15% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 101
\-------------------------

Environment.reset(): Trial set up with start = (7, 5), destination = (5, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.2198; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: 0.180659370736
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 0.18065937073603777, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent drove forward instead of right. (rewarded 0.18)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: right, reward: 2.55815679636
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.5581567963608487, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.56)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: right, reward: 1.14231484955
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.1423148495526365, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.14)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: -9.12555127893
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': -9.125551278931997, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.13)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: right, reward: 0.0867843555947
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.08678435559469222, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.09)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 1.33221906077
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.3322190607732094, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.33)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: forward, reward: 0.0965199554337
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.09651995543366065, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.10)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: None, reward: 1.80260482623
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.8026048262327548, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.80)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: None, reward: 1.2623339097
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.262333909700259, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.26)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: left, reward: 2.66624872798
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.6662487279847014, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.67)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: forward, reward: 2.41812941618
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 2.4181294161752898, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.42)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: left, reward: 0.675675723371
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 0.6756757233706872, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.68)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: right, reward: 0.0867518976897
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.08675189768969904, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.09)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: left, reward: 2.07666095242
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 2.076660952424797, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.08)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: left, reward: 0.568077633099
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': 0.5680776330992823, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.57)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: right, reward: 0.489672250219
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 0.4896722502186963, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 0.49)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 102
\-------------------------

Environment.reset(): Trial set up with start = (8, 7), destination = (4, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.2165; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2165; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.4450384822
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.4450384822043176, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.45)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.20993883579
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.209938835790153, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.45541353536
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.455413535364369, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.46)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.32499532254
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.324995322542852, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.32)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.94548547786
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.9454854778649864, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.95)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: left, reward: 0.952211773367
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 0.9522117733669497, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.95)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: right, reward: -0.0803292815286
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 19, 't': 6, 'action': 'right', 'reward': -0.08032928152860774, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded -0.08)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 2.63038316059
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.6303831605881536, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.63)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.25953592224
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.2595359222379223, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.26)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.75856281889
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.7585628188947908, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.76)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: left, reward: 1.45587707169
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 1.4558770716871394, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.46)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: right, reward: 1.77803202288
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.7780320228796513, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent followed the waypoint right. (rewarded 1.78)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 0.447231269355
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 0.4472312693552005, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.45)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: forward, reward: 0.233644493998
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'right'), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 0.23364449399846077, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'right')
Agent drove forward instead of left. (rewarded 0.23)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: -5.16037145578
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 14, 'action': None, 'reward': -5.160371455783663, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.16)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: forward, reward: 1.09229622576
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 1.0922962257565623, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.09)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: None, reward: 2.47102326139
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 16, 'action': None, 'reward': 2.4710232613877543, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.47)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: None, reward: 0.665552728779
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 8, 't': 17, 'action': None, 'reward': 0.6655527287793366, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.67)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: None, reward: 1.30214991451
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.3021499145057573, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.30)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: -0.47514614507
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 6, 't': 19, 'action': 'right', 'reward': -0.4751461450700146, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded -0.48)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 0.424276362561
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 20, 'action': 'right', 'reward': 0.42427636256097223, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.42)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: left, reward: -0.126263976869
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 4, 't': 21, 'action': 'left', 'reward': -0.1262639768688104, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded -0.13)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: 1.65410906778
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 3, 't': 22, 'action': 'forward', 'reward': 1.654109067777106, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.65)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: forward, reward: 0.36329753077
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 2, 't': 23, 'action': 'forward', 'reward': 0.3632975307701183, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.36)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: forward, reward: 0.726613247177
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 1, 't': 24, 'action': 'forward', 'reward': 0.7266132471767073, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.73)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 103
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (3, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.2133; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2133; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2133; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: left, reward: 2.01219881671
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.012198816710507, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.01)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: right, reward: 2.2665516988
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.266551698799421, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.27)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: right, reward: 0.079187315589
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.07918731558898562, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.08)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: forward, reward: 1.05518044017
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 1.055180440174646, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.06)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: left, reward: 1.93832813785
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.9383281378453776, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.94)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: left, reward: -20.9829472419
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 3, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': -20.98294724190331, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.98)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: 1.66914459012
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.6691445901193929, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.67)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 2.58180236262
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.5818023626166355, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.58)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 2.35898535972
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.3589853597184005, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.36)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: left, reward: 2.74446573281
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.744465732813647, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.74)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: 2.73243825365
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.7324382536487524, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.73)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.64680779367
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.6468077936687575, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.65)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: 1.41968831035
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 8, 't': 12, 'action': 'left', 'reward': 1.4196883103513673, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.42)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 0.678394606809
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 13, 'action': None, 'reward': 0.6783946068086062, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.68)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: -9.89858258136
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 6, 't': 14, 'action': 'left', 'reward': -9.89858258135777, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -9.90)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.3899658383
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.3899658382984077, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.39)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.0231204745614
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.023120474561350246, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove right instead of forward. (rewarded 0.02)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 1.32211497318
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.3221149731835253, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.32)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 0.797120984208
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.79712098420774, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.80)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 0.172292702434
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.17229270243372818, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.17)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 104
\-------------------------

Environment.reset(): Trial set up with start = (2, 5), destination = (6, 3), deadline = 30

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: right, reward: 0.632671870755
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 0.6326718707548302, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 0.63)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 1.3665902833
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.36659028330154, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.37)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: forward, reward: 1.87386319904
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': 1.8738631990359935, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.87)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 1.4086267654
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 1.4086267653983509, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 1.41)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: right, reward: 1.11477563823
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 1.1147756382257277, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.11)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: left, reward: 2.62895160702
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'left', 'reward': 2.628951607022734, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.63)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: left, reward: -9.83523652884
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 6, 'action': 'left', 'reward': -9.835236528837639, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.84)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 1.16302124573
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.1630212457277678, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.16)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 2.59603395777
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.5960339577695635, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.60)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: left, reward: 2.36857066718
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'left', 'reward': 2.3685706671781395, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.37)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: -9.49621954196
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': -9.496219541964635, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -9.50)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: left, reward: -20.850810973
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 19, 't': 11, 'action': 'left', 'reward': -20.85081097297634, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.85)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 1.04612308746
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 1.0461230874591267, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.05)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 1.26979754041
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 17, 't': 13, 'action': None, 'reward': 1.2697975404114423, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.27)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 1.70378232983
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 1.7037823298291372, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 1.70)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 0.835271100959
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 15, 't': 15, 'action': 'right', 'reward': 0.8352711009589764, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 0.84)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.37383055892
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.373830558915001, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.37)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 1.11615934418
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 1.1161593441754667, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent followed the waypoint right. (rewarded 1.12)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: -0.153644638627
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': -0.15364463862686084, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded -0.15)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: left, reward: 2.09649070536
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 19, 'action': 'left', 'reward': 2.0964907053556723, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.10)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 1.26925228097
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.2692522809698525, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.27)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 2.43029653726
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 21, 'action': 'forward', 'reward': 2.430296537255261, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.43)
27% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 105
\-------------------------

Environment.reset(): Trial set up with start = (2, 5), destination = (6, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.2070; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.05505987992
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.055059879915713, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.06)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.37321346291
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 29, 't': 1, 'action': None, 'reward': 1.3732134629121968, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.37)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.40804826163
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.4080482616275973, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.41)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.36713818978
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.367138189775238, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.37)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: 0.189394229904
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 0.1893942299036112, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.19)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: 2.6128498142
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 5, 'action': None, 'reward': 2.61284981419681, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.61)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: -4.96079015846
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 24, 't': 6, 'action': None, 'reward': -4.9607901584626095, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.96)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: left, reward: 2.52485399789
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 23, 't': 7, 'action': 'left', 'reward': 2.524853997890112, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.52)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 2.32774552627
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.3277455262685995, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.33)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 1.46119769801
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 1.461197698006755, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.46)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.14872979766
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': 1.1487297976608009, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.15)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: forward, reward: 1.60334715833
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': 1.6033471583268777, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.60)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: right, reward: 0.906529085114
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 0.9065290851137552, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.91)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: forward, reward: 1.25339924386
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 1.2533992438604549, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.25)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: None, reward: 2.13593617842
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 14, 'action': None, 'reward': 2.135936178417495, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: left, reward: -10.826008036
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 15, 'action': 'left', 'reward': -10.826008035999587, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.83)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: left, reward: 0.94586170567
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 14, 't': 16, 'action': 'left', 'reward': 0.9458617056702332, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 0.95)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 1.56566940945
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 17, 'action': None, 'reward': 1.5656694094490071, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.57)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 0.2171117222
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 0.21711172219996366, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 0.22)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: -0.171573019048
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 11, 't': 19, 'action': None, 'reward': -0.17157301904845845, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded -0.17)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 1.95044819529
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 10, 't': 20, 'action': 'right', 'reward': 1.9504481952870467, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.95)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: forward, reward: -0.428229213512
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 9, 't': 21, 'action': 'forward', 'reward': -0.4282292135120317, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded -0.43)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 2.29749988455
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 8, 't': 22, 'action': 'right', 'reward': 2.297499884553277, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.30)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: right, reward: 1.19267883665
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.1926788366535304, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.19)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.34389964585
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 24, 'action': None, 'reward': 1.3438996458477694, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.34)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: 0.482668065705
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 0.48266806570452014, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.48)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: left, reward: 0.732541444052
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 4, 't': 26, 'action': 'left', 'reward': 0.7325414440524991, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.73)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: forward, reward: 0.262748223519
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 3, 't': 27, 'action': 'forward', 'reward': 0.26274822351921223, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 0.26)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 0.212476540622
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 28, 'action': None, 'reward': 0.21247654062246357, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.21)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: 0.412747314662
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 1, 't': 29, 'action': 'right', 'reward': 0.41274731466233217, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.41)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 106
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (6, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.2039; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.2039; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: right, reward: 1.28531016306
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.2853101630597747, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.29)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: forward, reward: -10.4668160894
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': -10.466816089401053, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.47)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.84955553727
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.849555537265809, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.85)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 2.8788705247
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.8788705246980903, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.88)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.68959697598
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.6895969759750415, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.69)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 2.53211237579
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.532112375790508, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.53)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: left, reward: 1.84886496993
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.8488649699322957, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.85)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: right, reward: 1.13665811128
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 1.1366581112846184, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.14)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: forward, reward: 1.68854627513
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 1.6885462751291396, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.69)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.20402205122
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.204022051216065, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.20)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 1.22732191717
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.2273219171703877, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.23)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 2.56476091473
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 14, 't': 11, 'action': None, 'reward': 2.5647609147307455, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.56)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.09981022765
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.0998102276529653, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.10)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 2.73554983362
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 12, 't': 13, 'action': None, 'reward': 2.7355498336153046, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.74)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 0.888967024336
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 0.8889670243362655, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.89)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 2.3086708408
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 15, 'action': None, 'reward': 2.308670840801474, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.31)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: forward, reward: 1.71566846198
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 1.7156684619769782, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.72)
32% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 107
\-------------------------

Environment.reset(): Trial set up with start = (3, 5), destination = (7, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.2009; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 1.6003320752
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.6003320751967272, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.60)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: -5.52858738331
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 19, 't': 1, 'action': None, 'reward': -5.528587383306589, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.53)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 2.32167115304
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 2.3216711530436376, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.32)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 1.20176141931
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.2017614193069597, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.20)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 1.29067629442
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.2906762944177812, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.29)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: forward, reward: 2.17931463335
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.1793146333491804, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.18)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: forward, reward: 1.51195789036
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.5119578903558784, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.51)
65% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 108
\-------------------------

Environment.reset(): Trial set up with start = (2, 3), destination = (6, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.1979; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 1.16505912092
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.1650591209216037, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.17)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 1.78905491165
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.7890549116461067, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.79)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: right, reward: 0.768716446818
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.7687164468182858, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.77)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: 1.0363427091
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0363427091039505, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.04)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: right, reward: 2.80455064038
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 2.8045506403782214, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.80)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 1.20935106673
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.2093510667282743, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.21)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 1.20128397225
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.2012839722544542, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.20)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 0.775240903186
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.7752409031857304, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.78)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: right, reward: 0.778533585026
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.778533585026118, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.78)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: right, reward: 1.00355866985
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.0035586698483039, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 1.00)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 2.7439430869
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 2.74394308690413, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.74)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 0.608429208901
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.6084292089009589, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.61)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 1.52870816434
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 8, 't': 12, 'action': 'left', 'reward': 1.5287081643382663, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.53)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 2.23179787878
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 2.2317978787751658, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.23)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: 2.0301709215
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': 2.030170921504783, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.03)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: left, reward: 1.66920616692
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.6692061669245724, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.67)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 109
\-------------------------

Environment.reset(): Trial set up with start = (7, 7), destination = (4, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.1950; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1950; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1950; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1950; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: right, reward: 1.29676372422
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'forward'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.2967637242196373, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'forward')
Agent drove right instead of forward. (rewarded 1.30)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: right, reward: 1.22192726381
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.2219272638146825, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.22)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: None, reward: -4.06084546239
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': None, 'reward': -4.060845462387734, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.06)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: right, reward: 1.31091139205
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 1.310911392051511, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.31)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: left, reward: 1.16108173325
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.1610817332502834, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.16)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 0.0264682342212
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.02646823422122646, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.03)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: None, reward: -5.95388688509
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': -5.9538868850922135, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.95)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: left, reward: 1.74999925671
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 1.7499992567128793, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.75)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: forward, reward: 1.16502101768
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 1.1650210176818834, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.17)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 2.56020447759
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 2.560204477591493, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.56)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: None, reward: 1.66963302481
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.6696330248098317, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.67)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: 1.560939868
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.5609398679976214, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.56)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: 0.792631292709
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 0.7926312927094401, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.79)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 110
\-------------------------

Environment.reset(): Trial set up with start = (6, 4), destination = (2, 2), deadline = 30
Simulating trial. . . 
epsilon = 0.1920; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: right, reward: 1.34993984169
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 1.3499398416914812, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.35)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: right, reward: 1.8954230526
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.895423052600348, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.90)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: forward, reward: 1.70060322241
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': 1.7006032224146899, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.70)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: 0.97472523795
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 27, 't': 3, 'action': 'forward', 'reward': 0.9747252379500566, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent followed the waypoint forward. (rewarded 0.97)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: forward, reward: 1.99280240909
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 1.9928024090882892, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.99)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: right, reward: 0.242383580134
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.2423835801337345, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.24)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: right, reward: 2.18662500255
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 2.1866250025529457, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 2.19)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: right, reward: 1.02482966991
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 1.0248296699068276, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.02)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: 0.246205371627
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 22, 't': 8, 'action': 'left', 'reward': 0.24620537162743605, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.25)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 2.14661448624
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 2.1466144862372403, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.15)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: 1.24798813547
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 20, 't': 10, 'action': 'right', 'reward': 1.2479881354739775, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.25)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: -20.9152859555
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 19, 't': 11, 'action': 'right', 'reward': -20.915285955497332, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.92)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: None, reward: 2.22746364211
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.2274636421085523, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.23)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: forward, reward: 2.7427668367
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 2.7427668367026783, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.74)
53% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 111
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (5, 4), deadline = 30
Simulating trial. . . 
epsilon = 0.1892; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1892; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: forward, reward: 1.21219173253
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': 1.212191732531617, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.21)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 1.55488064078
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.5548806407828848, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.55)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: right, reward: 1.6457903866
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.6457903866002805, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.65)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: right, reward: 1.78101375303
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 1.7810137530300638, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.78)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: None, reward: 1.20116876808
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.2011687680788663, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.20)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: right, reward: 2.90955670114
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 2.909556701137258, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 2.91)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.74272286761
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 24, 't': 6, 'action': None, 'reward': 2.7427228676145265, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.74)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: 2.81193701508
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 2.8119370150845318, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.81)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: forward, reward: 2.5107617233
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'right'), 'deadline': 22, 't': 8, 'action': 'forward', 'reward': 2.510761723303405, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'right')
Agent followed the waypoint forward. (rewarded 2.51)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: None, reward: 0.986621325664
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 9, 'action': None, 'reward': 0.9866213256642113, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.99)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 1.32676185
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 1.3267618499991578, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent followed the waypoint forward. (rewarded 1.33)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: right, reward: 2.52276262493
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 2.5227626249325503, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.52)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: 2.46816166299
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.468161662993629, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.47)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: right, reward: 0.37909732357
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 0.3790973235695212, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.38)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 1.22668163021
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 14, 'action': None, 'reward': 1.2266816302138044, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.23)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 1.65810509627
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.6581050962670403, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.66)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: left, reward: 0.940015129212
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': 0.9400151292117813, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.94)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 0.9718197417
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 13, 't': 17, 'action': None, 'reward': 0.971819741699659, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.97)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: forward, reward: -39.0488206691
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 18, 'action': 'forward', 'reward': -39.0488206691398, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.05)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.5386484443
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 19, 'action': None, 'reward': 1.5386484442991073, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.54)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: -0.266402454961
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 10, 't': 20, 'action': 'right', 'reward': -0.26640245496135706, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded -0.27)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: -0.200909328787
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 9, 't': 21, 'action': None, 'reward': -0.2009093287869631, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded -0.20)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: left, reward: -10.0486066054
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 8, 't': 22, 'action': 'left', 'reward': -10.048606605371694, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent attempted driving left through a red light. (rewarded -10.05)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: right, reward: 1.86364282252
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.8636428225205148, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.86)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: right, reward: 0.697062229603
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 6, 't': 24, 'action': 'right', 'reward': 0.6970622296029783, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 0.70)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 0.693879165316
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 0.6938791653156351, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.69)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.98530430793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 4, 't': 26, 'action': None, 'reward': 1.9853043079256836, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.99)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.81896120515
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 3, 't': 27, 'action': None, 'reward': 1.818961205148886, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.82)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: 0.326750843041
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 2, 't': 28, 'action': 'right', 'reward': 0.32675084304096147, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.33)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: -0.901172820076
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 1, 't': 29, 'action': None, 'reward': -0.9011728200756692, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded -0.90)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 112
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (8, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.1864; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1864; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1864; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1864; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: forward, reward: 2.04573656657
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 2.045736566568837, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 2.05)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.81128221727
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.8112822172662346, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.81)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 2.86235116179
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.862351161790592, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.86)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: left, reward: -9.93331849517
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': -9.933318495168884, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.93)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 2.28397686545
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.2839768654485564, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.28)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.81203738205
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.8120373820459914, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.81)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: 1.54891511056
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 1.5489151105608858, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.55)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: forward, reward: 2.14995025495
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 2.1499502549467415, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.15)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: left, reward: 0.991505089379
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 17, 't': 8, 'action': 'left', 'reward': 0.9915050893791747, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.99)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 2.36804983654
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 2.368049836539569, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.37)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: 0.175064256827
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 0.17506425682665772, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 0.18)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 1.51794518054
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.5179451805399031, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent drove forward instead of right. (rewarded 1.52)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: None, reward: 0.506280566792
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'forward'), 'deadline': 13, 't': 12, 'action': None, 'reward': 0.5062805667924601, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 0.51)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 1.13795716879
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 1.1379571687918852, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.14)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: right, reward: 2.41932398568
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 2.4193239856831923, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.42)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 1.25022428707
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 1.2502242870723095, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.25)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: left, reward: 2.40224931023
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'left', 'reward': 2.402249310232447, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.40)
32% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 113
\-------------------------

Environment.reset(): Trial set up with start = (7, 5), destination = (4, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.1836; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1836; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: left, reward: 1.20792334709
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 1.207923347090249, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.21)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: 1.5636722657
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.5636722656985191, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.56)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: forward, reward: 1.37959948933
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 1.3795994893285703, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.38)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 2.80868421819
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.808684218185231, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.81)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: forward, reward: 2.45296605896
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.452966058962012, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.45)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: forward, reward: -9.12590169508
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': -9.125901695084448, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -9.13)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 0.617964895338
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.6179648953380732, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.62)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 1.8558711105
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.8558711105037546, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.86)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 1.30011108113
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.3001110811258043, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.30)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: left, reward: 1.7672703209
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.7672703208972234, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.77)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 2.57745068017
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 2.577450680172362, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.58)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 114
\-------------------------

Environment.reset(): Trial set up with start = (8, 2), destination = (3, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.1809; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1809; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: right, reward: 2.821366709
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.821366708996215, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.82)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: right, reward: 1.01661665308
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.0166166530780296, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.02)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 0.351808393965
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.35180839396459873, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 0.35)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: left, reward: 1.29153520312
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.2915352031210636, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.29)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: 2.46148201631
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.4614820163133784, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.46)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: left, reward: 0.289470956433
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 0.2894709564329716, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.29)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: forward, reward: 0.858654115871
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.8586541158713648, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded 0.86)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: right, reward: 1.2281538715
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.2281538715013658, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.23)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: right, reward: 2.34112492694
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.341124926936909, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.34)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 115
\-------------------------

Environment.reset(): Trial set up with start = (4, 3), destination = (8, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.1782; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: left, reward: 2.14015332965
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 30, 't': 0, 'action': 'left', 'reward': 2.14015332964552, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.14)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 2.84085813509
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 29, 't': 1, 'action': None, 'reward': 2.8408581350880784, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.84)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 1.34269345499
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.3426934549887266, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.34)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 1.56972313285
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.5697231328534949, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.57)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 2.61469884403
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 26, 't': 4, 'action': None, 'reward': 2.6146988440272283, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.61)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 0.31111545286
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.31111545285953557, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.31)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: forward, reward: 2.02981218536
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 2.029812185364845, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.03)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: forward, reward: 1.74556887136
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 1.7455688713616961, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.75)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 2.00035803481
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 8, 'action': 'forward', 'reward': 2.0003580348058687, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.00)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 1.97784907961
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 9, 'action': None, 'reward': 1.9778490796113837, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.98)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 1.96668481981
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 20, 't': 10, 'action': None, 'reward': 1.9666848198095632, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.97)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 0.913490724126
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 11, 'action': None, 'reward': 0.9134907241264778, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.91)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 2.42183927401
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.4218392740079646, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.42)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: forward, reward: 0.954837715046
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 0.9548377150463467, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 0.95)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: left, reward: 1.60578078337
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 1.605780783365386, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.61)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: None, reward: 2.58784739775
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 15, 't': 15, 'action': None, 'reward': 2.587847397752867, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.59)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: None, reward: 1.82214187816
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.8221418781616392, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.82)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: left, reward: 2.20787974157
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 17, 'action': 'left', 'reward': 2.207879741571725, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.21)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 116
\-------------------------

Environment.reset(): Trial set up with start = (5, 4), destination = (6, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.1755; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1755; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: forward, reward: 1.60049696921
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.6004969692121698, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent drove forward instead of right. (rewarded 1.60)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: left, reward: 1.46754640688
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.4675464068772355, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.47)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: left, reward: 0.978275107804
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 0.9782751078036604, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.98)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: None, reward: 2.4094500225
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.409450022504184, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.41)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: right, reward: 0.436430640069
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.43643064006896115, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.44)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 1.90557994532
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.9055799453221458, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.91)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 0.95279523987
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.9527952398702497, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.95)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: forward, reward: -39.2839686707
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': -39.28396867067349, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.28)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: left, reward: -39.8741442157
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': 'left', 'reward': -39.874144215685554, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.87)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: left, reward: 1.07648368114
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.0764836811378038, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.08)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: None, reward: 2.20603841349
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.2060384134926405, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 2.21)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: forward, reward: 0.793543538104
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 0.793543538104228, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.79)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: right, reward: 0.173748308901
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.1737483089013392, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.17)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: right, reward: 1.16970394944
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 1.1697039494400059, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.17)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: right, reward: 1.72660287302
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.726602873021367, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent followed the waypoint right. (rewarded 1.73)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 0.67444192695
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 5, 't': 15, 'action': None, 'reward': 0.674441926949517, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.67)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: left, reward: -9.65644833583
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': -9.656448335833682, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.66)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: forward, reward: 0.593978596612
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 0.5939785966117219, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.59)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: None, reward: 0.416602133676
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.4166021336760348, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.42)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: None, reward: 1.83010304996
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.8301030499634305, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.83)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 117
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (5, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.1729; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1729; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1729; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1729; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: left, reward: 1.58162751662
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 30, 't': 0, 'action': 'left', 'reward': 1.581627516623699, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.58)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: forward, reward: 1.56557486778
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 29, 't': 1, 'action': 'forward', 'reward': 1.56557486777805, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.57)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 2.07970440528
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 28, 't': 2, 'action': None, 'reward': 2.0797044052764386, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.08)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 1.2924810546
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.292481054600733, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.29)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: left, reward: -9.20359614052
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 26, 't': 4, 'action': 'left', 'reward': -9.203596140524207, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.20)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 1.71383653867
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 25, 't': 5, 'action': None, 'reward': 1.7138365386669012, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.71)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: forward, reward: 2.89098753532
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 2.8909875353156718, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 2.89)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: right, reward: 0.877334709198
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 0.87733470919806, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.88)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: right, reward: 0.911250388028
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 0.9112503880278188, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.91)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: None, reward: 2.811296898
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 21, 't': 9, 'action': None, 'reward': 2.811296898003873, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.81)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: left, reward: 1.12712186587
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': 1.1271218658660107, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.13)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 2.81130935586
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 2.811309355856838, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.81)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: right, reward: 0.744709333801
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'right'), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 0.7447093338009884, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'right')
Agent drove right instead of left. (rewarded 0.74)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: left, reward: 0.955769436497
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 0.9557694364973488, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.96)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: left, reward: 0.813586847537
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 0.813586847536939, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 0.81)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: forward, reward: 0.907235885954
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 15, 'action': 'forward', 'reward': 0.9072358859538001, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.91)
47% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 118
\-------------------------

Environment.reset(): Trial set up with start = (3, 5), destination = (7, 4), deadline = 25
Simulating trial. . . 
epsilon = 0.1703; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 1.67035735762
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.6703573576205213, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.67)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 0.472888028526
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 0.4728880285257926, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 0.47)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 1.75720976807
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.7572097680654892, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.76)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: left, reward: 1.56125596553
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 1.5612559655321996, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.56)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 2.85480638801
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.8548063880080345, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.85)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.06389300122
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.0638930012167371, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.06)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.10526220614
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.1052622061443018, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.11)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: forward, reward: 1.16118832765
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.1611883276494548, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.16)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: forward, reward: 1.61794208485
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 1.6179420848497628, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.62)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: left, reward: -10.798652676
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 9, 'action': 'left', 'reward': -10.798652676019175, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -10.80)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: forward, reward: 0.507071955869
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 0.5070719558692024, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.51)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: forward, reward: 1.23899855914
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.2389985591408053, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 1.24)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: forward, reward: 0.496890424159
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 0.49689042415883367, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 0.50)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: forward, reward: -10.2364962141
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': -10.236496214131709, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.24)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 1.65908726242
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.6590872624238686, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.66)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 0.561609263684
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 0.5616092636839198, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.56)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: right, reward: 2.22099653999
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 2.220996539991405, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.22)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 2.4135414977
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 17, 'action': None, 'reward': 2.4135414977006437, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.41)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 2.11144969096
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 2.111449690957958, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.11)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 1.4476805759
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': 1.447680575899064, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.45)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 2.36280968566
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 5, 't': 20, 'action': None, 'reward': 2.3628096856572682, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.36)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: 1.75800644098
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': 1.758006440982994, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.76)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: left, reward: 1.07889627521
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 3, 't': 22, 'action': 'left', 'reward': 1.0788962752073066, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.08)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: forward, reward: 0.772573128137
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 2, 't': 23, 'action': 'forward', 'reward': 0.7725731281370345, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.77)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: None, reward: 0.101107860934
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 24, 'action': None, 'reward': 0.10110786093372548, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.10)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 119
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (8, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.1678; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 0.955360335018
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 0.9553603350182429, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.96)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 0.622993587652
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 19, 't': 1, 'action': None, 'reward': 0.6229935876521958, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.62)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 1.47227797714
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.472277977144766, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.47)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: forward, reward: -9.15407174738
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': -9.15407174738243, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -9.15)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: right, reward: 1.06339983783
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.0633998378296374, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.06)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 1.77150237392
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.7715023739204987, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.77)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 1.28891380564
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.2889138056351743, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 1.29)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: None, reward: 0.0722546296089
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': 0.07225462960890106, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.07)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: right, reward: 0.981978941743
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.9819789417427931, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.98)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 1.7142280586
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.714228058598541, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.71)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 1.51863007382
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.5186300738188747, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.52)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: right, reward: 2.63621984097
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 2.6362198409739603, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.64)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 0.0202094326225
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.02020943262252195, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.02)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: -20.7798269456
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 7, 't': 13, 'action': 'right', 'reward': -20.7798269456272, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.78)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: right, reward: 1.91941454188
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.919414541883491, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.92)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 1.43740579534
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 1.4374057953440198, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.44)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: forward, reward: 1.28680893586
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', 'left'), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 1.2868089358646448, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'left')
Agent drove forward instead of right. (rewarded 1.29)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 1.96521840987
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 1.9652184098678238, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.97)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 0.654132429725
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.6541324297254281, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.65)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 1.2341319969
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.2341319969036195, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.23)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 120
\-------------------------

Environment.reset(): Trial set up with start = (3, 6), destination = (2, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.1653; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1653; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 2.78887589725
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.7888758972468084, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.79)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.92966391156
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.9296639115602687, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.93)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.84512390641
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.8451239064101894, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.85)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 2.13474931806
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.134749318057385, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.13)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: 2.39476911357
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.3947691135707263, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.39)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: 2.4430088264
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.443008826398707, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.44)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: None, reward: 2.47955806466
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.479558064663153, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.48)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: 2.34783179428
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.347831794278336, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.35)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: right, reward: 0.5471726659
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.5471726658995429, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.55)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 1.45501594783
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.4550159478338476, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.46)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: left, reward: 1.45419557161
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 1.4541955716061914, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.45)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: 0.979702936846
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 0.9797029368456269, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.98)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 1.2437014254
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'forward'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.2437014254003558, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.24)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 0.779504497168
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.7795044971681343, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.78)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 1.34423322305
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.3442332230509, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent drove right instead of left. (rewarded 1.34)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 0.737365768472
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 0.7373657684715886, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.74)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 0.425832455095
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.42583245509468526, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.43)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: -9.62502816342
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': -9.625028163416406, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -9.63)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 0.824342018232
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.824342018232217, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 0.82)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: -20.0407123254
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 3, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -20.040712325434953, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -20.04)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 121
\-------------------------

Environment.reset(): Trial set up with start = (3, 5), destination = (8, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.1628; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.57254471333
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.5725447133271215, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.57)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: left, reward: -10.6037344591
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': -10.603734459146523, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.60)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.34099989191
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.340999891911446, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.34)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.74431499768
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.7443149976794885, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.27954353173
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.279543531725092, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.28)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: left, reward: 2.51570651384
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 2.5157065138406547, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.52)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.74807379182
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.748073791821842, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.75)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.08269502496
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.0826950249648999, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.08)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 2.8437058655
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.843705865503904, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.84)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: -0.0206086576845
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': -0.020608657684459963, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded -0.02)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: left, reward: 2.50047812309
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 2.5004781230902564, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.50)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.58309847483
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 11, 'action': None, 'reward': 1.583098474834635, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.58)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.40623938161
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.4062393816099468, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.41)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 1.22260728222
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 1.2226072822231866, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.22)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 1.08875475508
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 1.0887547550768737, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.09)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 122
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (5, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.1604; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.14004689777
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.1400468977714924, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.14)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: right, reward: 0.595513008319
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 0.5955130083193427, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.60)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 2.6292760075
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.6292760074993087, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.63)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 2.16686105034
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.1668610503420824, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.17)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 1.04018391431
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.0401839143101286, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.04)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 1.71315369126
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.7131536912638339, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.71)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: -5.48920953819
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': -5.489209538189851, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.49)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: right, reward: 1.10364070375
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 1.1036407037501457, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 1.10)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.58325660866
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.5832566086562814, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.58)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: left, reward: 2.22009392762
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 2.2200939276249816, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.22)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: forward, reward: 1.44662078715
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.446620787147999, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.45)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 2.45723925583
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 2.4572392558270026, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.46)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: -10.6588836889
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': -10.658883688853814, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -10.66)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: right, reward: 0.224648294516
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 0.22464829451557522, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.22)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: left, reward: 2.12279329091
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 14, 'action': 'left', 'reward': 2.1227932909107174, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.12)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: forward, reward: 1.69351682511
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 1.693516825112649, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.69)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: None, reward: 1.77702356304
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 9, 't': 16, 'action': None, 'reward': 1.7770235630414888, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.78)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: None, reward: 1.51909676691
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 8, 't': 17, 'action': None, 'reward': 1.5190967669058777, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.52)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: None, reward: 1.00741123187
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.0074112318738149, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.01)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: forward, reward: 1.35100484001
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': 1.3510048400060024, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.35)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 1.76061590152
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 20, 'action': None, 'reward': 1.7606159015216616, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.76)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: left, reward: 1.34734551601
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 4, 't': 21, 'action': 'left', 'reward': 1.3473455160056238, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.35)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 0.680053315064
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 3, 't': 22, 'action': None, 'reward': 0.6800533150644525, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.68)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 1.30088688765
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 2, 't': 23, 'action': None, 'reward': 1.3008868876451585, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.30)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 1.05913907998
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 1, 't': 24, 'action': None, 'reward': 1.059139079976962, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.06)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 123
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (2, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.1580; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1580; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: None, reward: 2.95868607975
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.9586860797547, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.96)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: None, reward: 2.18173799909
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.181737999091666, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.18)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: None, reward: 1.93650866813
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.9365086681310744, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.94)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: None, reward: 1.43066636646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.4306663664640755, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.43)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: None, reward: 2.70935783361
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.7093578336059694, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.71)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: forward, reward: 1.92482863337
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 1.9248286333715834, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.92)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: left, reward: 1.12817054195
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.128170541949231, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.13)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.63575377913
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.6357537791276004, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.64)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: right, reward: 1.18681998559
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 1.1868199855902608, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.19)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: None, reward: 2.43004247144
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 2.430042471440534, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.43)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: left, reward: -10.0981303053
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 15, 't': 10, 'action': 'left', 'reward': -10.09813030528834, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent attempted driving left through a red light. (rewarded -10.10)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: left, reward: 1.81981661945
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 1.8198166194534615, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.82)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: forward, reward: 1.38704862809
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 1.3870486280875527, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.39)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: right, reward: 2.33769324135
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 2.337693241352805, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.34)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: None, reward: 1.5372029056
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.5372029055997822, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.54)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 1.4131918988
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 1.4131918987983798, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.41)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: 2.08750971479
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 9, 't': 16, 'action': 'left', 'reward': 2.087509714794364, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.09)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: None, reward: 1.77615438786
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'forward'), 'deadline': 8, 't': 17, 'action': None, 'reward': 1.7761543878554384, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.78)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: None, reward: 1.37863380658
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.3786338065785977, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.38)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: forward, reward: -0.12688016306
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': -0.1268801630601647, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded -0.13)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: left, reward: 1.30062011531
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 5, 't': 20, 'action': 'left', 'reward': 1.3006201153147572, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.30)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: 0.68427676813
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 4, 't': 21, 'action': None, 'reward': 0.6842767681295736, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.68)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: right, reward: -0.0772243553719
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 3, 't': 22, 'action': 'right', 'reward': -0.07722435537194561, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded -0.08)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 0.232054051043
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 2, 't': 23, 'action': 'right', 'reward': 0.23205405104255572, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.23)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 1.55257698824
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 1, 't': 24, 'action': 'right', 'reward': 1.552576988236161, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.55)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 124
\-------------------------

Environment.reset(): Trial set up with start = (3, 2), destination = (6, 4), deadline = 25
Simulating trial. . . 
epsilon = 0.1557; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1557; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1557; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: None, reward: 2.92627787902
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.9262778790247186, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.93)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: None, reward: 1.76208788204
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.7620878820392685, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.76)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: None, reward: 2.80454308434
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.804543084336302, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.80)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: None, reward: 1.51508925398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.515089253977764, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.52)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: forward, reward: -10.1665677426
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': -10.16656774261837, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent attempted driving forward through a red light. (rewarded -10.17)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: right, reward: 0.52999601408
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.529996014080203, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.53)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 1.91187913088
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 1.9118791308823586, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.91)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: forward, reward: 1.57064666752
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.5706466675221926, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.57)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: forward, reward: 0.0855510566759
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 0.0855510566759018, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove forward instead of left. (rewarded 0.09)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: left, reward: 1.51701992594
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 1.5170199259413537, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.52)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: forward, reward: 1.38329300665
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.3832930066478157, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.38)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 0.913357883102
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 11, 'action': None, 'reward': 0.9133578831015892, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.91)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.88890444786
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.8889044478635368, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.89)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.80980004667
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.8098000466694502, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.81)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 0.947626113096
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 11, 't': 14, 'action': None, 'reward': 0.9476261130963741, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.95)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.98910623411
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 10, 't': 15, 'action': None, 'reward': 1.9891062341083567, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.99)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: forward, reward: 1.66602938669
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 1.6660293866919806, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.67)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: None, reward: 2.40292544311
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 17, 'action': None, 'reward': 2.4029254431085656, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.40)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: None, reward: 1.85977042991
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.8597704299050308, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.86)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: None, reward: 0.576435320561
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 6, 't': 19, 'action': None, 'reward': 0.5764353205608232, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.58)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: None, reward: 1.40979533732
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 5, 't': 20, 'action': None, 'reward': 1.4097953373153733, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.41)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: forward, reward: 2.21063208827
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': 2.2106320882745796, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.21)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 0.541476257802
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 3, 't': 22, 'action': 'right', 'reward': 0.5414762578015997, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 0.54)
8% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 125
\-------------------------

Environment.reset(): Trial set up with start = (1, 3), destination = (6, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.1534; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1534; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1534; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1534; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.23743073433
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'left'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.2374307343338875, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'left')
Agent followed the waypoint right. (rewarded 1.24)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 1.49504724528
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.4950472452794505, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.50)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: forward, reward: 2.54796226588
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 2.54796226587729, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.55)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 2.39609097787
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.3960909778729675, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.40)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 2.01272175996
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.012721759960883, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.01)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: forward, reward: 2.43887940925
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.438879409250993, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.44)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 126
\-------------------------

Environment.reset(): Trial set up with start = (8, 7), destination = (2, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.1511; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1511; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: forward, reward: -40.5740281911
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'right'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'right', 'right'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': -40.574028191096076, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'right')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -40.57)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: None, reward: 2.64965162244
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.6496516224353797, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.65)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: None, reward: 1.86000740587
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.8600074058720588, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 1.86)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: None, reward: 1.50163167058
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.5016316705831951, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.50)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: None, reward: 2.93142296045
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.931422960446394, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.93)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: left, reward: 2.5954673599
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.5954673598990254, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.60)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 1.38046206127
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.3804620612748406, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.38)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: forward, reward: 2.75943663376
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.7594366337617573, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.76)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: right, reward: 1.3262782031
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.3262782030997222, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.33)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: None, reward: 1.45393066273
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.4539306627276214, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.45)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: -9.24415427674
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': -9.24415427673701, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -9.24)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: right, reward: 0.77262021653
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.7726202165301748, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.77)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 2.45015410307
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': 2.4501541030679492, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.45)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: left, reward: 1.92606157556
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.9260615755625718, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.93)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: 2.37994132351
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 6, 't': 14, 'action': None, 'reward': 2.3799413235094353, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.38)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 0.731421476316
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 0.7314214763159521, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.73)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 0.54888518902
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.5488851890195439, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.55)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: forward, reward: 0.200922881846
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 0.20092288184610585, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 0.20)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 0.0287969629656
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.02879696296559664, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 0.03)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: right, reward: 0.584507907597
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 0.5845079075970152, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.58)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 127
\-------------------------

Environment.reset(): Trial set up with start = (8, 4), destination = (1, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.1488; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 2.67677523591
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.676775235907367, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.68)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.70724514485
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.707245144851598, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.71)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.33482405377
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.3348240537711937, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.33)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: left, reward: -9.9566310236
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -9.956631023596959, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.96)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 2.09087114143
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.0908711414290737, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.09)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.16190624027
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.1619062402689122, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.16)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: left, reward: 2.55605655142
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 2.5560565514154217, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.56)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.20510952886
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.205109528856836, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.08762241876
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.0876224187643297, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.09)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 0.47669079126
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'right'), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 0.4766907912596108, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'right')
Agent drove forward instead of left. (rewarded 0.48)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: -10.7925122974
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': -10.792512297376106, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.79)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: left, reward: 1.07660548769
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.076605487689589, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.08)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: right, reward: 0.578293821948
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.5782938219476139, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.58)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 2.46226286259
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 7, 't': 13, 'action': None, 'reward': 2.462262862586277, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.46)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 1.3166907998
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.3166907998029451, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.32)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: left, reward: 0.541061706941
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 0.5410617069412753, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 0.54)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: left, reward: 1.87202151642
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 1.8720215164186231, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.87)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: 1.81803877787
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.8180387778653757, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.82)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: 0.766011000309
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.7660110003089797, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.77)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: left, reward: 0.765521788675
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 1, 't': 19, 'action': 'left', 'reward': 0.7655217886747213, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.77)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 128
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (6, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.1466; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1466; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1466; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: right, reward: 1.79121312512
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.7912131251185046, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 1.79)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: left, reward: -10.0492156325
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': -10.049215632488453, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.05)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: None, reward: 2.42618506808
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.4261850680816606, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.43)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: None, reward: 2.74377748631
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.7437774863050324, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: forward, reward: 2.77736728328
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 2.77736728327722, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.78)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 1.11554728857
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.1155472885702271, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.12)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: forward, reward: 2.47667854907
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.4766785490748235, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.48)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: forward, reward: -10.2344019512
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': -10.234401951186824, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.23)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 1.65513852467
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.6551385246684118, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.66)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: forward, reward: 1.54818725692
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 1.548187256922615, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.55)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: None, reward: 1.59351286597
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.593512865966571, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.59)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: left, reward: 1.75953844423
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 1.7595384442338857, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.76)
52% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 129
\-------------------------

Environment.reset(): Trial set up with start = (4, 7), destination = (6, 4), deadline = 25
Simulating trial. . . 
epsilon = 0.1444; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: left, reward: 2.60883179064
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'left', 'reward': 2.6088317906416063, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.61)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: None, reward: 2.61959339974
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.619593399741904, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.62)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: 1.95267228931
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.952672289307498, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.95)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: right, reward: 0.862460665941
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 0.8624606659411913, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.86)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: left, reward: 1.67461222744
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.6746122274410107, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.67)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 2.38336819624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.383368196242019, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.38)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 1.41640775425
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.4164077542484093, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.42)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: left, reward: 1.62215351619
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 1.6221535161923293, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.62)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: 1.2103261024
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 1.2103261024028535, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.21)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: right, reward: 1.74971139274
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 1.7497113927353105, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.75)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 130
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (2, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.1423; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: forward, reward: 0.0377688267284
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 0.037768826728441285, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove forward instead of right. (rewarded 0.04)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: right, reward: 2.64125106946
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 2.6412510694611866, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent followed the waypoint right. (rewarded 2.64)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: right, reward: 1.77100806355
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.771008063553546, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.77)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: 1.45857971812
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.4585797181237645, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.46)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: left, reward: -9.21120232597
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': -9.211202325969843, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.21)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: right, reward: 0.152812880428
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.15281288042811603, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.15)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: left, reward: 2.41822451452
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 2.418224514517635, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.42)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 2.25980400921
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.259804009211886, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.26)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 2.55638841669
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.5563884166886437, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.56)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: None, reward: 1.71907340514
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.719073405135772, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.72)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: left, reward: 2.22006113018
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 2.220061130184348, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.22)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: 2.64754259784
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 2.647542597840074, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.65)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 0.141911482559
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 0.14191148255890496, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.14)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 1.45819089595
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.4581908959546215, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.46)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.38426730143
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 11, 't': 14, 'action': None, 'reward': 2.3842673014289164, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.38)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.33632851798
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 15, 'action': None, 'reward': 2.3363285179757423, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.34)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 0.91591053265
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 16, 'action': None, 'reward': 0.9159105326500854, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.92)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: left, reward: 0.958839524646
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 17, 'action': 'left', 'reward': 0.9588395246455546, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.96)
28% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 131
\-------------------------

Environment.reset(): Trial set up with start = (6, 4), destination = (5, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.1402; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: 0.455508242638
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 0.4555082426384267, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 0.46)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: right, reward: 1.26113470716
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.261134707158315, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.26)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: forward, reward: 1.04229915702
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 1.0422991570168825, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 1.04)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: right, reward: 2.83166911403
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 2.831669114025294, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.83)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: None, reward: 1.52467077559
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.5246707755885338, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.52)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: left, reward: -10.0982004882
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': -10.098200488244936, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -10.10)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: right, reward: 1.2173510439
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.217351043900001, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.22)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: left, reward: 2.33314390813
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 2.333143908133864, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.33)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: None, reward: 2.23892728398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.2389272839762335, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.24)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: forward, reward: 1.43526878328
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.4352687832824669, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.44)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 132
\-------------------------

Environment.reset(): Trial set up with start = (7, 5), destination = (5, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.1381; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1381; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: -4.68154503149
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': -4.681545031489728, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.68)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: left, reward: 1.83990896863
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.8399089686340724, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.84)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: left, reward: 1.23131594285
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.2313159428462872, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.23)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 1.37420104989
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.3742010498870623, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.37)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 1.9363990755
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.9363990754974114, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.94)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 1.18391145417
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.183911454166264, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.18)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: forward, reward: 2.32984887635
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.329848876347015, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.33)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: right, reward: 1.48473725926
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.4847372592568917, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.48)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: None, reward: 2.38609948264
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.386099482637159, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.39)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: forward, reward: 2.29354289076
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.293542890759497, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.29)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: forward, reward: 2.26576130943
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 2.2657613094285463, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.27)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 133
\-------------------------

Environment.reset(): Trial set up with start = (7, 5), destination = (6, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.1360; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: 1.36748547914
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.3674854791403352, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent drove forward instead of right. (rewarded 1.37)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: right, reward: 1.08780776114
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.0878077611441048, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.09)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: right, reward: 2.67320257208
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.6732025720803776, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.67)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: right, reward: 0.349575402629
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.3495754026285377, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.35)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 1.65727735764
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.6572773576441744, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.66)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 2.30290887257
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.3029088725677216, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.30)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: forward, reward: 0.535549434368
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.5355494343681351, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.54)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: -0.0379141456199
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': -0.03791414561986817, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded -0.04)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: forward, reward: -39.6669167615
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': -39.666916761530906, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent attempted driving forward through a red light with traffic and cause a major accident. (rewarded -39.67)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.57170746799
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.5717074679881156, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.57)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.67813353399
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.6781335339884182, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.68)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: left, reward: 1.06492428957
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.064924289573134, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.06)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 2.39482770173
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 2.394827701732403, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.39)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 1.41615698541
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 1.416156985409935, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.42)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 0.60027687569
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 0.6002768756904073, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.60)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 0.8063312299
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 0.8063312299002543, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.81)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: left, reward: 1.56150915148
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 1.5615091514843797, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.56)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 1.84600091709
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'left', 'reward': 1.8460009170907052, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.85)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 1.56456621557
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.564566215571189, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.56)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 1.36439502746
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.3643950274602439, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.36)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 134
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (8, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.1340; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: right, reward: 0.76355568557
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 0.7635556855698831, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 0.76)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: None, reward: 1.54697393588
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 29, 't': 1, 'action': None, 'reward': 1.5469739358782246, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.55)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: None, reward: 1.35301608961
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.3530160896102499, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.35)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: None, reward: 1.2397033093
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.239703309302949, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.24)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: 1.06904048763
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 1.0690404876263626, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.07)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: right, reward: 0.995027661651
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.9950276616512311, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.00)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: None, reward: 1.58417533635
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 6, 'action': None, 'reward': 1.5841753363504412, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.58)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: left, reward: 1.4378303656
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 23, 't': 7, 'action': 'left', 'reward': 1.4378303656022573, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.44)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 1.46621468135
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 1.4662146813549386, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 1.47)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 2.4593297811
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 9, 'action': None, 'reward': 2.459329781095689, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.46)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 2.73693913886
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': 2.7369391388615645, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: right, reward: 0.229777118318
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 0.22977711831830006, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 0.23)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: right, reward: 2.32853742189
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 2.328537421892168, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 2.33)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 2.50009337271
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 2.500093372707588, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.50)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 0.717987048672
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 0.7179870486715407, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.72)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: right, reward: 0.427354695812
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 15, 'action': 'right', 'reward': 0.4273546958121749, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.43)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: right, reward: 1.57274650077
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'right', 'reward': 1.5727465007650374, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.57)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: forward, reward: -10.8845371293
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': -10.884537129333065, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -10.88)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 0.793655874392
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 0.7936558743917363, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.79)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: forward, reward: 1.09319189239
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': 1.0931918923931392, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.09)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: forward, reward: 1.32521083309
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 10, 't': 20, 'action': 'forward', 'reward': 1.3252108330882235, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 1.33)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: right, reward: 1.76388539633
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 9, 't': 21, 'action': 'right', 'reward': 1.763885396328777, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.76)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: None, reward: 0.377440052889
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 8, 't': 22, 'action': None, 'reward': 0.3774400528892865, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.38)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: right, reward: 1.38718020513
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.387180205134367, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.39)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 135
\-------------------------

Environment.reset(): Trial set up with start = (7, 2), destination = (4, 5), deadline = 30
Simulating trial. . . 
epsilon = 0.1320; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 2.47085677981
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 2.470856779814816, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.47)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 1.03439420389
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.0343942038887564, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.03)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 2.55508769261
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 28, 't': 2, 'action': None, 'reward': 2.5550876926094936, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.56)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 0.516815994046
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 0.5168159940460159, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.52)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: left, reward: -39.9174535809
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 26, 't': 4, 'action': 'left', 'reward': -39.91745358086131, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.92)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 1.49115264575
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 25, 't': 5, 'action': None, 'reward': 1.4911526457496331, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 1.49)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: forward, reward: 1.82580332806
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 1.8258033280594281, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 1.83)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 1.57868949645
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 1.578689496445627, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.58)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: forward, reward: 1.3022585218
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 22, 't': 8, 'action': 'forward', 'reward': 1.3022585217993146, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 1.30)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: forward, reward: -0.0933370001919
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': -0.09333700019193092, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded -0.09)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 2.57663318384
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 20, 't': 10, 'action': None, 'reward': 2.5766331838405447, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.58)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: left, reward: 1.59900605357
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 19, 't': 11, 'action': 'left', 'reward': 1.59900605356893, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.60)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.69693438372
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.696934383723853, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.70)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 2.47697130324
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 2.476971303238744, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.48)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.701539021571
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 0.701539021570696, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent drove right instead of forward. (rewarded 0.70)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 2.25499634697
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 15, 't': 15, 'action': 'left', 'reward': 2.2549963469720105, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.25)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: 2.19900429968
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 14, 't': 16, 'action': None, 'reward': 2.1990042996784105, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.20)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: left, reward: 0.0464290468525
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 13, 't': 17, 'action': 'left', 'reward': 0.046429046852505707, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 0.05)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: right, reward: 0.810108911898
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 0.8101089118983655, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.81)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: forward, reward: 1.20859185944
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': 1.2085918594390521, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 1.21)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: right, reward: 0.925792726974
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 20, 'action': 'right', 'reward': 0.925792726974008, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.93)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: right, reward: 1.11578586823
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 9, 't': 21, 'action': 'right', 'reward': 1.1157858682301112, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.12)
27% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 136
\-------------------------

Environment.reset(): Trial set up with start = (1, 2), destination = (4, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.1300; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: 1.1993508285
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.1993508285015269, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 1.20)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: right, reward: 1.86000263082
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.8600026308216022, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.86)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: right, reward: 2.87657277059
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.8765727705931656, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.88)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 0.0213533616616
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.021353361661578307, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.02)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: left, reward: 1.41407591131
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.41407591130868, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.41)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: -5.33671163861
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': -5.336711638605578, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.34)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: forward, reward: 1.15020247282
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.1502024728235558, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.15)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: 1.25264153169
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.2526415316850394, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.25)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: 1.29151991594
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.2915199159423256, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.29)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: left, reward: 0.912801330582
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 0.9128013305822058, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.91)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 137
\-------------------------

Environment.reset(): Trial set up with start = (7, 5), destination = (2, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.1281; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: 2.52989724187
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 2.5298972418691643, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.53)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.20563112767
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.205631127673265, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: -10.0149542194
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': -10.014954219374333, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -10.01)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: right, reward: 0.291063506274
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 0.2910635062741833, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.29)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: None, reward: 2.00356806903
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.003568069031364, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.00)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: None, reward: 1.47706986646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.4770698664621107, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.48)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: None, reward: 1.27089401471
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.2708940147065704, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.27)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: left, reward: 2.02890056514
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 2.0289005651369574, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.03)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: forward, reward: 1.77451031934
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 1.7745103193391574, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.77)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 0.638846230824
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 0.6388462308242511, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.64)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 1.10392705641
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.1039270564099297, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.10)
56% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 138
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (4, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.1262; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: None, reward: 1.96189498631
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.96189498631385, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.96)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: left, reward: -10.3140010022
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': -10.314001002157143, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -10.31)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 0.662520883346
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 0.6625208833460248, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.66)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.80230301758
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.8023030175848573, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.80)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 2.87381114769
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.873811147687551, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.87)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: 1.20784458812
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 1.2078445881204103, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.21)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: -9.13791491144
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': -9.137914911439266, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.14)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: left, reward: 1.79329623307
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 1.7932962330737894, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.79)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: None, reward: 2.75339492826
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.753394928258478, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.75)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: forward, reward: 1.43483029063
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 1.434830290625809, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.43)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: forward, reward: 2.44094437572
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 2.440944375724457, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.44)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: right, reward: 1.22380039436
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.2238003943606819, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.22)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: 1.37684987422
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.376849874219728, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.38)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: forward, reward: 0.821015681007
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 0.821015681006849, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.82)
44% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 139
\-------------------------

Environment.reset(): Trial set up with start = (3, 6), destination = (7, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.1243; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1243; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1243; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1243; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 2.82763346063
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.827633460627248, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.83)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.12817928529
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.1281792852869044, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.13)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 2.66184081802
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.661840818020738, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.66)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 2.65544951163
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.6554495116349703, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.66)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: right, reward: 0.634167979432
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 0.634167979431694, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove right instead of left. (rewarded 0.63)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: None, reward: 2.07331622176
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.073316221758276, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.07)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: None, reward: 1.10681574509
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.106815745092834, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.11)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: forward, reward: 2.41782960021
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 2.4178296002111654, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent followed the waypoint forward. (rewarded 2.42)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 2.36596767412
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.3659676741165923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.37)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.30531227872
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.3053122787228884, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: forward, reward: 1.21280060282
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.2128006028238232, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.21)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: forward, reward: 1.75624452994
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.7562445299407035, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.76)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 1.40290183374
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 1.4029018337358257, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.40)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 140
\-------------------------

Environment.reset(): Trial set up with start = (5, 2), destination = (3, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.1225; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1225; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 1.0192435559
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.0192435558992092, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 1.02)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: forward, reward: 1.78205122109
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.7820512210938468, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove forward instead of left. (rewarded 1.78)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: left, reward: 2.74962445002
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 2.749624450017362, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.75)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: 1.33221627087
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 1.3322162708716743, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.33)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.70959268945
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.7095926894500018, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.71)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.48226126048
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.4822612604767786, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.48)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 2.06890372632
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 2.068903726318325, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.07)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 2.26359348888
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.263593488875509, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.26)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: None, reward: 1.39852560747
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.398525607472546, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.40)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: left, reward: 0.474335941864
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 0.47433594186390726, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 0.47)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: 0.824060494373
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 0.824060494373283, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.82)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: -0.0735601894042
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 9, 't': 11, 'action': None, 'reward': -0.07356018940421483, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded -0.07)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: -0.313683357248
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 8, 't': 12, 'action': None, 'reward': -0.3136833572480726, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded -0.31)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: right, reward: 2.40453808775
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 2.4045380877463103, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.40)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 141
\-------------------------

Environment.reset(): Trial set up with start = (2, 3), destination = (5, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.1206; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: right, reward: 0.317214838204
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 0.31721483820385976, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.32)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: None, reward: 2.34185243854
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.3418524385374355, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.34)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: None, reward: 2.26775709089
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.2677570908897793, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.27)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: None, reward: 2.70673267557
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.70673267557245, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.71)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: None, reward: 2.76910511465
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.7691051146541454, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.77)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: None, reward: 1.72382735666
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.7238273566610964, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.72)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: left, reward: 1.47963063001
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.4796306300071305, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.48)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: forward, reward: 0.99714191076
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 0.9971419107601416, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.00)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 1.39864195548
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.3986419554833949, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.40)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 0.952953350583
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 9, 'action': None, 'reward': 0.9529533505826671, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.95)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: None, reward: 0.938098111441
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 15, 't': 10, 'action': None, 'reward': 0.9380981114409466, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 0.94)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: left, reward: 1.21635919481
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 1.2163591948095087, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent drove left instead of forward. (rewarded 1.22)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: right, reward: 2.0326172723
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 2.0326172723032565, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.03)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: 1.8682503562
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.8682503561962778, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.87)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: 1.37055232408
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.3705523240808501, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.37)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: right, reward: 0.329034098536
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 0.3290340985359117, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.33)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: right, reward: 2.38758727609
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 2.3875872760877836, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.39)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: right, reward: 2.1679213963
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 8, 't': 17, 'action': 'right', 'reward': 2.167921396301373, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.17)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: right, reward: 1.75281837037
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 7, 't': 18, 'action': 'right', 'reward': 1.7528183703686266, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.75)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: right, reward: 0.123285416259
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 6, 't': 19, 'action': 'right', 'reward': 0.12328541625932121, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.12)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: right, reward: 1.33487997148
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 5, 't': 20, 'action': 'right', 'reward': 1.3348799714754513, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.33)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: right, reward: 0.780727866336
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 4, 't': 21, 'action': 'right', 'reward': 0.7807278663364834, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 0.78)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: right, reward: 1.77826290287
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 3, 't': 22, 'action': 'right', 'reward': 1.7782629028651975, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.78)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: left, reward: 0.397259940174
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 2, 't': 23, 'action': 'left', 'reward': 0.39725994017412725, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 0.40)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: right, reward: -0.497669021062
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 1, 't': 24, 'action': 'right', 'reward': -0.4976690210615988, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded -0.50)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 142
\-------------------------

Environment.reset(): Trial set up with start = (5, 4), destination = (3, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.1188; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: right, reward: 1.96705218923
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.967052189228149, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.97)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: right, reward: 2.09476942856
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.094769428561195, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.09)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: right, reward: 2.32134497554
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.3213449755432842, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.32)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 1.84940706981
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.8494070698132679, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.85)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: right, reward: 1.72267946854
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.7226794685415174, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.72)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: None, reward: 1.97497411378
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.9749741137824341, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.97)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: None, reward: 2.20570805237
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.205708052374005, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: None, reward: 2.09555144595
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.0955514459514455, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.10)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: None, reward: 2.29723018036
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.297230180363537, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.30)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: left, reward: 2.70083887117
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.7008388711681457, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.70)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 2.0466531208
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.0466531207972816, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.05)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: forward, reward: 0.916068438516
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 0.916068438515595, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 0.92)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: right, reward: 0.0937132900308
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.09371329003075646, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.09)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: forward, reward: 1.06758300236
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.0675830023612844, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.07)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 1.4481685885
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.4481685885015358, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.45)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 1.0415849559
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 1.041584955898469, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent drove right instead of forward. (rewarded 1.04)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: -4.13839504582
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 4, 't': 16, 'action': None, 'reward': -4.138395045817123, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.14)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: 2.02194335795
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 2.021943357953975, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.02)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: 1.56312692103
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.5631269210268353, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.56)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: 0.487326858612
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.48732685861231406, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.49)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 143
\-------------------------

Environment.reset(): Trial set up with start = (3, 5), destination = (8, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.1171; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: 1.18812334467
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.1881233446681403, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.19)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: 0.434264087049
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.4342640870491209, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.43)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: left, reward: 1.87340265565
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.8734026556498353, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.87)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.39579907766
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.3957990776588804, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.40)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 2.87893008561
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.8789300856145292, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.88)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 1.61924448496
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.6192444849564898, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.62)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 144
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (7, 7), deadline = 35
Simulating trial. . . 
epsilon = 0.1153; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1153; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: right, reward: 0.856214266552
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 35, 't': 0, 'action': 'right', 'reward': 0.856214266552364, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.86)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: None, reward: 1.48588669073
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'right'), 'deadline': 34, 't': 1, 'action': None, 'reward': 1.4858866907332773, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.49)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: right, reward: 1.96642881222
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 33, 't': 2, 'action': 'right', 'reward': 1.9664288122168752, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.97)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: forward, reward: 1.85802422516
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 32, 't': 3, 'action': 'forward', 'reward': 1.8580242251596646, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.86)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: right, reward: 0.526064604949
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 31, 't': 4, 'action': 'right', 'reward': 0.5260646049494948, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.53)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: left, reward: 2.22734739854
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 30, 't': 5, 'action': 'left', 'reward': 2.2273473985361685, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.23)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: forward, reward: 1.33244565407
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 29, 't': 6, 'action': 'forward', 'reward': 1.332445654074398, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.33)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: 1.02380548046
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 28, 't': 7, 'action': None, 'reward': 1.0238054804575394, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.02)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: 2.55091659812
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 27, 't': 8, 'action': None, 'reward': 2.5509165981222575, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.55)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: 2.3697043908
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 26, 't': 9, 'action': 'left', 'reward': 2.369704390804581, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.37)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: None, reward: 1.77824977398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 25, 't': 10, 'action': None, 'reward': 1.7782497739809324, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.78)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: None, reward: 2.24877917886
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 24, 't': 11, 'action': None, 'reward': 2.248779178864959, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.25)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: None, reward: 1.69017613818
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 23, 't': 12, 'action': None, 'reward': 1.6901761381767475, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.69)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: forward, reward: 2.40852032021
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 22, 't': 13, 'action': 'forward', 'reward': 2.408520320213392, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.41)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: None, reward: 2.52389768457
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 14, 'action': None, 'reward': 2.5238976845689445, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.52)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: None, reward: 1.8316772744
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 20, 't': 15, 'action': None, 'reward': 1.831677274399724, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.83)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: None, reward: -4.9023850105
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 16, 'action': None, 'reward': -4.902385010504531, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.90)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: forward, reward: 0.885880611009
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 18, 't': 17, 'action': 'forward', 'reward': 0.8858806110094877, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.89)
49% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 145
\-------------------------

Environment.reset(): Trial set up with start = (6, 2), destination = (3, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.1136; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1136; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 2.52679509415
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.526795094147574, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.53)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 2.10911735316
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.1091173531633407, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.11)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 1.64949136428
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.6494913642817153, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.65)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 1.1104831923
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.1104831923046257, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.11)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: forward, reward: 1.10552464215
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.105524642153422, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.11)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 1.25244446644
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.252444466444783, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.25)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: forward, reward: -10.2742810533
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': -10.27428105325894, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.27)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 2.20457248297
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.204572482972059, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.20)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 0.836060634602
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 0.8360606346023993, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.84)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: left, reward: 1.30315782448
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.3031578244766882, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.30)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: forward, reward: 2.71498109571
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 2.7149810957118206, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.71)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: left, reward: 2.07226470978
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 2.0722647097799296, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.07)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: forward, reward: 2.41354326527
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 2.413543265273277, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.41)
35% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 146
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (1, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.1119; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1119; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1119; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 2.94114457149
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.941144571487243, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.94)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 2.69386471946
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.693864719461727, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.69)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 2.05918710336
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.0591871033634144, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.06)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 2.10703824653
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.10703824652749, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.11)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 2.56040880013
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.5604088001300234, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.56)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: forward, reward: 1.02977410409
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 1.0297741040866484, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.03)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: 2.56880142381
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.568801423808572, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.57)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 0.930905589055
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 18, 't': 7, 'action': None, 'reward': 0.9309055890545759, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.93)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.26157632124
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 1.2615763212447533, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent drove right instead of left. (rewarded 1.26)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: forward, reward: 2.72793238255
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 2.727932382554391, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.73)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: right, reward: 1.59671262179
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'forward'), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.5967126217869358, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'forward')
Agent drove right instead of forward. (rewarded 1.60)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 6), heading: (0, 1), action: left, reward: 1.77876685765
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 1.7787668576519136, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.78)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: left, reward: 1.14709514198
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 1.1470951419801596, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.15)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 147
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (7, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.1103; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: None, reward: 0.866299427308
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 0.8662994273075775, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.87)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: right, reward: 1.09436443597
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'right'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.09436443596738, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'right')
Agent followed the waypoint right. (rewarded 1.09)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: right, reward: 1.50870346177
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.5087034617675184, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.51)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 1.64406024264
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.644060242637226, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.64)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: forward, reward: 1.20973260082
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.2097326008238998, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.21)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: 1.8535114836
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.8535114835956892, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.85)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: left, reward: 1.15259897854
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.1525989785378916, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.15)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: left, reward: 1.76708106863
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.7670810686329768, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.77)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: None, reward: 1.08539660026
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.085396600261046, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.09)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: None, reward: 1.37280697649
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.3728069764912587, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.37)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: forward, reward: 2.29457418475
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'right'), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 2.2945741847497745, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'right')
Agent followed the waypoint forward. (rewarded 2.29)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: forward, reward: 2.64287680708
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 2.6428768070829225, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.64)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 148
\-------------------------

Environment.reset(): Trial set up with start = (4, 3), destination = (6, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.1086; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 1.78514417722
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.7851441772196226, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.79)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 1.88513241847
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.885132418466194, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.89)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 1.9534936066
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.9534936066035964, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.95)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 1.02527245032
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0252724503220079, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.03)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: left, reward: 2.05126804016
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 2.051268040164233, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.05)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: 1.82193705226
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.821937052259853, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.82)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: right, reward: 1.05396775793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.053967757927313, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.05)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: forward, reward: 1.28681160763
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.2868116076275637, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.29)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 2.36811227425
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.3681122742460916, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.37)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: None, reward: 2.00024559431
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.000245594314436, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 2.00)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: left, reward: 1.94686144246
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 1.9468614424632122, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.95)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 149
\-------------------------

Environment.reset(): Trial set up with start = (3, 3), destination = (6, 6), deadline = 30
Simulating trial. . . 
epsilon = 0.1070; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: right, reward: 1.52124378476
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 1.521243784756608, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.52)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: None, reward: 2.95754481003
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 29, 't': 1, 'action': None, 'reward': 2.957544810031792, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.96)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: None, reward: 1.31271381972
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.3127138197190387, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: None, reward: 1.2847589701
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.2847589700998057, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.28)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: forward, reward: 2.45661934694
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 2.456619346937498, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.46)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: 2.28102690115
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 2.2810269011465008, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.28)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: 2.68316298693
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 24, 't': 6, 'action': 'left', 'reward': 2.6831629869256757, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.68)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: forward, reward: 1.49745505661
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 1.4974550566064653, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent followed the waypoint forward. (rewarded 1.50)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: forward, reward: 2.4533832198
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 22, 't': 8, 'action': 'forward', 'reward': 2.4533832198014807, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.45)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 150
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (8, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.1054; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: None, reward: 1.68468549634
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.6846854963381488, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.68)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 1.2491055894
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.2491055893989838, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.25)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 2.15309086376
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.1530908637619497, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.15)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 2.39503057467
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.3950305746675173, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.40)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 1.79637928692
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.796379286921844, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.80)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: forward, reward: 2.31712005939
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.317120059391167, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.32)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 2.10371119347
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 2.103711193465286, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.10)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: right, reward: 0.619517348971
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 0.6195173489708887, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.62)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: forward, reward: 1.68642267549
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 1.6864226754858298, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove forward instead of left. (rewarded 1.69)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: right, reward: 1.47208299535
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 1.472082995349119, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.47)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: left, reward: 2.78035159823
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 2.7803515982321576, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.78)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: left, reward: 1.16539408355
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 1.16539408355038, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.17)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: -5.43721437427
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 13, 't': 12, 'action': None, 'reward': -5.437214374273131, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.44)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.06806545513
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.0680654551319033, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.07)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.79336685502
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.7933668550194044, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.79)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 2.08290825009
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 2.082908250094033, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.08)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 1.16781772325
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 1.167817723254291, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.17)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 0.589140897739
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 8, 't': 17, 'action': None, 'reward': 0.589140897739203, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.59)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 1.66448698794
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.6644869879377513, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.66)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 0.898200632652
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 19, 'action': None, 'reward': 0.898200632652173, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.90)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 0.558752275975
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 5, 't': 20, 'action': None, 'reward': 0.5587522759754471, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.56)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: left, reward: 0.73498081174
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 21, 'action': 'left', 'reward': 0.7349808117396559, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.73)
12% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 151
\-------------------------

Environment.reset(): Trial set up with start = (5, 4), destination = (8, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.1038; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: forward, reward: 0.989102118411
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 0.9891021184112181, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove forward instead of left. (rewarded 0.99)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: right, reward: 0.603576689567
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.6035766895665297, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.60)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: forward, reward: 2.30765913438
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 2.3076591343840738, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.31)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: 2.79698883809
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.796988838087776, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.80)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: 0.561091223536
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.5610912235364461, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.56)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: 2.68319517728
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.6831951772822773, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.68)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: forward, reward: 0.61565231221
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.6156523122095392, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.62)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: left, reward: -40.1457617813
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': -40.14576178128422, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.15)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: None, reward: 1.55677063855
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.5567706385464464, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.56)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: left, reward: 1.7324147548
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.7324147548048676, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.73)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.64769361639
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.647693616393959, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.65)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 1.62787447597
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.62787447597113, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.63)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 0.879807358446
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': 0.879807358445519, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.88)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: left, reward: 1.61202698136
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.6120269813620434, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.61)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 1.92318184892
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'left'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.9231818489208024, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'left')
Agent followed the waypoint right. (rewarded 1.92)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: left, reward: 1.15601002974
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.1560100297375802, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.16)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: None, reward: 0.376003784137
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 4, 't': 16, 'action': None, 'reward': 0.3760037841373487, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.38)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: right, reward: 0.693698005416
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 0.6936980054163351, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.69)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: right, reward: 0.544300013038
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 0.5443000130375768, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.54)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: 1.51546950409
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 1.5154695040933197, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.52)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 152
\-------------------------

Environment.reset(): Trial set up with start = (7, 7), destination = (2, 4), deadline = 30
Simulating trial. . . 
epsilon = 0.1023; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1023; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1023; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1023; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 2.29262322859
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 30, 't': 0, 'action': None, 'reward': 2.292623228588109, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.29)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 2.01557707958
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 29, 't': 1, 'action': None, 'reward': 2.0155770795769286, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.02)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 1.8392544174
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.8392544174040308, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.84)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 1.41629408102
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.4162940810178708, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.42)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 1.57206010162
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.5720601016210554, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.57)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 1.85328835277
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 25, 't': 5, 'action': None, 'reward': 1.8532883527738715, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.85)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: left, reward: 1.28501328125
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 24, 't': 6, 'action': 'left', 'reward': 1.2850132812477275, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.29)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 2.51933444765
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 2.519334447650373, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.52)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 2.84234785544
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.8423478554449955, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.84)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 0.999417042267
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 9, 'action': None, 'reward': 0.9994170422667277, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 1.63244947376
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 20, 't': 10, 'action': 'right', 'reward': 1.6324494737567226, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.63)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 2.10091540025
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 2.100915400253956, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.10)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 1.09983965199
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.0998396519923663, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.10)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: left, reward: 1.77978373898
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 1.7797837389845819, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.78)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: left, reward: 2.19050178025
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 2.1905017802465836, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.19)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: right, reward: 1.34316438616
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 15, 't': 15, 'action': 'right', 'reward': 1.3431643861593758, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.34)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 2.43026623041
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 2.4302662304071774, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.43)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: forward, reward: 0.119550203446
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'right'), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 0.11955020344552114, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'right')
Agent drove forward instead of left. (rewarded 0.12)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 0.857844942012
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 18, 'action': None, 'reward': 0.8578449420117231, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.86)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 2.43994251679
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 19, 'action': None, 'reward': 2.439942516789801, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.44)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: None, reward: 0.617148914839
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 10, 't': 20, 'action': None, 'reward': 0.6171489148393006, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.62)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: 0.629276706374
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'left', 'reward': 0.629276706374257, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.63)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: forward, reward: 1.2891850471
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 8, 't': 22, 'action': 'forward', 'reward': 1.289185047096637, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.29)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: right, reward: 1.24238974582
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.2423897458151827, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.24)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: left, reward: 2.23721771228
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 6, 't': 24, 'action': 'left', 'reward': 2.23721771228262, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.24)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 0.258236892663
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 0.25823689266301275, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.26)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: None, reward: 2.20504301736
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 4, 't': 26, 'action': None, 'reward': 2.205043017356058, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: 0.957830387301
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 3, 't': 27, 'action': 'forward', 'reward': 0.9578303873006011, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.96)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: None, reward: 1.94883994617
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 2, 't': 28, 'action': None, 'reward': 1.9488399461738946, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.95)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: forward, reward: 0.512492365499
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 1, 't': 29, 'action': 'forward', 'reward': 0.512492365498612, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.51)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 153
\-------------------------

Environment.reset(): Trial set up with start = (2, 3), destination = (8, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.1008; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1008; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1008; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.1008; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 2.72699128591
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.726991285912414, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.73)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.51745184832
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.5174518483218176, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.52)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.14363632344
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.143636323443171, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.14)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.07722484525
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.0772248452498, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.08)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: forward, reward: 1.7407435971
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.7407435970983993, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.74)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.7694606977
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.7694606977009177, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.77)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.04492810762
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.044928107619989, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.04)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 2.30255504413
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 2.3025550441256635, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.30)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: None, reward: 2.41594765981
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.4159476598075402, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.42)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: forward, reward: 1.82699018907
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.8269901890666342, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.83)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 154
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (6, 4), deadline = 30
Simulating trial. . . 
epsilon = 0.0993; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 1.63317318661
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': 1.6331731866120984, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.63)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.26511721571
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 29, 't': 1, 'action': None, 'reward': 1.265117215705754, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.27)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 1.12405141766
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.1240514176593548, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.12)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.64708084339
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 2.6470808433872492, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.65)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.31505255635
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 2.3150525563452495, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.32)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: left, reward: 1.74013443024
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'left', 'reward': 1.7401344302381252, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.74)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.74498061751
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 6, 'action': None, 'reward': 1.7449806175119598, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.74)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 5), heading: (-1, 0), action: None, reward: 1.33569900644
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.335699006443147, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.34)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: right, reward: 1.89258714843
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 1.8925871484306813, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.89)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 1.53148793762
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 9, 'action': None, 'reward': 1.5314879376237052, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.53)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: None, reward: 1.01151211252
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': 1.0115121125202358, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.01)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: forward, reward: 0.574634210067
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': 0.5746342100665388, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.57)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: None, reward: 1.74829839957
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.7482983995676242, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.75)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: left, reward: 1.61085478041
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 1.61085478040633, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.61)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 1.8097033471
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 16, 't': 14, 'action': None, 'reward': 1.8097033471043285, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.81)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 1.70332378769
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.7033237876858613, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.70)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: None, reward: 2.51790324958
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 14, 't': 16, 'action': None, 'reward': 2.5179032495801517, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.52)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 1.23759534193
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 1.23759534192871, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.24)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: left, reward: 1.49480329532
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 12, 't': 18, 'action': 'left', 'reward': 1.4948032953221744, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.49)
37% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 155
\-------------------------

Environment.reset(): Trial set up with start = (3, 7), destination = (7, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.0978; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0978; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0978; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0978; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0978; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: right, reward: 1.68199578084
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 1.6819957808386874, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.68)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: right, reward: 2.88106240607
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 2.8810624060695593, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.88)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 0.882970857801
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 0.8829708578007406, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.88)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: None, reward: 1.55638188452
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.5563818845157051, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.56)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: None, reward: 1.86410889083
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.8641088908295584, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.86)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: left, reward: 2.11695931415
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 25, 't': 5, 'action': 'left', 'reward': 2.116959314147996, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.12)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 2.86200700942
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'forward'), 'deadline': 24, 't': 6, 'action': None, 'reward': 2.8620070094184085, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 2.86)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 2.65371527798
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 2.653715277977451, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.65)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 1.92797410866
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.9279741086585243, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.93)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 1.21424085433
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 1.2142408543273222, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.21)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 1.46004518971
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 20, 't': 10, 'action': None, 'reward': 1.4600451897106215, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.46)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 1.55553592653
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 1.555535926527592, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.56)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 1.62839197721
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.6283919772057431, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.63)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: 1.7314978557
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 1.731497855704455, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.73)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 2.34071304511
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 14, 'action': None, 'reward': 2.340713045112293, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.34)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: -10.1071575611
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 15, 'action': 'left', 'reward': -10.107157561059413, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.11)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: left, reward: 1.24978265436
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'left', 'reward': 1.249782654364276, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.25)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: forward, reward: 2.065106012
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 2.0651060120036044, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.07)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: forward, reward: 1.19354310154
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 18, 'action': 'forward', 'reward': 1.1935431015373175, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.19)
37% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 156
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (8, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0963; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: left, reward: -39.0798641464
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': -39.07986414636779, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.08)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: 2.46765287847
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.467652878469666, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.47)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: 1.13863212677
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.1386321267685315, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.14)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: left, reward: 1.51103875939
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.5110387593902956, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.51)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: None, reward: 1.25356224656
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.2535622465613394, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.25)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: left, reward: 1.3922244601
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.3922244600992812, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.39)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: None, reward: 2.54010143844
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.5401014384448355, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.54)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: None, reward: 2.32106591251
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.3210659125133173, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.32)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: None, reward: 2.23210852861
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.2321085286147815, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.23)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: left, reward: -39.2745236623
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': -39.27452366234954, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.27)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: None, reward: 1.82202120509
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.8220212050858784, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.82)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: forward, reward: 2.32277808783
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 2.322778087833128, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.32)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: right, reward: 0.901374271218
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.9013742712180679, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.90)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: forward, reward: 0.949562107265
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 0.9495621072645067, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.95)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: right, reward: -0.335445308908
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': -0.3354453089076067, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded -0.34)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 0.390725637877
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': 0.3907256378767585, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent drove forward instead of right. (rewarded 0.39)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: right, reward: 1.60905086219
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 1.6090508621881392, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.61)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: right, reward: 1.65649634477
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 1.65649634477396, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.66)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 1.16476604892
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.1647660489162461, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.16)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 0.465521053859
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.46552105385944254, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.47)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 157
\-------------------------

Environment.reset(): Trial set up with start = (5, 6), destination = (6, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0949; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0949; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0949; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0949; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 1.58438507908
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.5843850790811278, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.58)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 1.06853379434
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.0685337943419704, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.07)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: left, reward: 1.6122129901
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.6122129901044906, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.61)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: None, reward: -4.03261392011
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': -4.032613920106807, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.03)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: left, reward: 2.161373521
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 2.161373521001978, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.16)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: 1.16592276758
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.1659227675761854, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.17)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 1.34982590843
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.3498259084278246, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.35)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 1.35499024372
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.3549902437157797, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.35)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: None, reward: 1.6863556013
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.6863556012973804, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.69)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: forward, reward: 1.40391665939
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.4039166593931105, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.40)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: None, reward: 0.956437839841
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 0.956437839840593, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.96)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: left, reward: 1.28680193419
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.2868019341874952, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.29)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 158
\-------------------------

Environment.reset(): Trial set up with start = (3, 7), destination = (7, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.0935; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0935; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0935; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: None, reward: -4.38454240948
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 30, 't': 0, 'action': None, 'reward': -4.3845424094844265, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent idled at a green light with no oncoming traffic. (rewarded -4.38)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: left, reward: 0.672742089914
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 29, 't': 1, 'action': 'left', 'reward': 0.6727420899141044, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.67)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: right, reward: 0.148892727552
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 0.14889272755196126, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.15)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: None, reward: 1.59352603677
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.593526036773777, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.59)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: right, reward: 1.14702667466
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 1.147026674664879, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.15)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: 0.979790277333
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 0.9797902773328278, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.98)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 1.45654152257
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.4565415225730387, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.46)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: left, reward: 2.82471502759
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 23, 't': 7, 'action': 'left', 'reward': 2.8247150275884527, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.82)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 2.73105104983
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.731051049826222, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.73)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 1.8998396054
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 1.8998396054047262, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.90)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: 1.4326550193
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 1.4326550193009329, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.43)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: right, reward: 1.30994859123
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 1.3099485912311417, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 1.31)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: left, reward: -0.0234007125153
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 18, 't': 12, 'action': 'left', 'reward': -0.023400712515290523, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded -0.02)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: None, reward: 1.51298867592
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 17, 't': 13, 'action': None, 'reward': 1.5129886759222249, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.51)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: None, reward: 0.975037247003
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 16, 't': 14, 'action': None, 'reward': 0.9750372470028623, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.98)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: None, reward: 1.64012195378
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.640121953782729, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.64)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 1.38593190293
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 14, 't': 16, 'action': 'forward', 'reward': 1.3859319029348958, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.39)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: left, reward: 2.0973994962
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 17, 'action': 'left', 'reward': 2.097399496202681, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.10)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: left, reward: 1.81360354203
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 12, 't': 18, 'action': 'left', 'reward': 1.8136035420282854, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.81)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: left, reward: -9.77713931395
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 11, 't': 19, 'action': 'left', 'reward': -9.777139313948314, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent attempted driving left through a red light. (rewarded -9.78)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 0.472500966626
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 10, 't': 20, 'action': 'right', 'reward': 0.47250096662617924, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.47)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: left, reward: 2.027224807
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'left', 'reward': 2.0272248070006187, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.03)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 1.20474255749
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 8, 't': 22, 'action': 'forward', 'reward': 1.2047425574884136, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 1.20)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 1.78175935827
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.7817593582702063, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.78)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: 0.172481610527
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 6, 't': 24, 'action': 'left', 'reward': 0.17248161052665822, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.17)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: -9.19624076934
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 5, 't': 25, 'action': 'forward', 'reward': -9.196240769335988, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent attempted driving forward through a red light. (rewarded -9.20)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 0.53088677698
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'forward'), 'deadline': 4, 't': 26, 'action': None, 'reward': 0.5308867769801282, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 0.53)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 0.262385121808
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 3, 't': 27, 'action': 'right', 'reward': 0.26238512180807194, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 0.26)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 0.944446721611
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 2, 't': 28, 'action': 'right', 'reward': 0.9444467216108003, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.94)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.81327814312
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 29, 'action': None, 'reward': 1.8132781431245377, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.81)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 159
\-------------------------

Environment.reset(): Trial set up with start = (7, 2), destination = (8, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0921; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: 1.40927311675
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.4092731167450085, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 1.41)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 1.70866537407
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.7086653740680462, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.71)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 0.981639989549
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 0.9816399895494061, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.98)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 1.85501082123
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.8550108212279217, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.86)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 0.234146296867
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.23414629686650767, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.23)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: right, reward: 1.55285651749
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.5528565174891553, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent followed the waypoint right. (rewarded 1.55)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 0.123052954639
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 14, 't': 6, 'action': None, 'reward': 0.12305295463932575, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.12)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: 0.945196079802
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 0.9451960798024088, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 0.95)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 2.4312113504
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.431211350396424, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.43)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 1.99122044691
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.9912204469136612, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.99)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: -5.64057020713
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': None, 'reward': -5.640570207129789, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.64)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.46149705807
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.461497058073731, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.46)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: right, reward: 1.00524050911
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.0052405091124255, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.01)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 0.739590853789
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 7, 't': 13, 'action': None, 'reward': 0.7395908537893787, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.74)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 1.63911760575
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.639117605750676, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.64)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 1.16913538373
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.1691353837296714, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.17)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 0.92852027907
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.9285202790696343, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.93)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: -19.5384424226
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 3, 't': 17, 'action': 'right', 'reward': -19.53844242259583, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.54)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 2.00747774466
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 2.007477744658469, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.01)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: left, reward: -40.612685374
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 1, 't': 19, 'action': 'left', 'reward': -40.612685374031535, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.61)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 160
\-------------------------

Environment.reset(): Trial set up with start = (6, 5), destination = (3, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0907; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0907; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 2.05188811387
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.051888113874564, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.05)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 2.86269504773
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.86269504773344, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.86)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.00000393568
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.0000039356771862, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.00)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 2.49643507116
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.496435071155208, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.50)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.18772124855
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.1877212485543995, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.19)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 0.992417402572
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 0.992417402571836, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.99)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: right, reward: 0.861379643272
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.8613796432719043, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.86)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.77087436647
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.7708743664685398, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.77)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.08922209044
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.089222090444054, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.09)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.73778664227
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.737786642273407, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.74)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.53646380999
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.5364638099911987, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.54)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: left, reward: 1.05126197937
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.0512619793664841, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.05)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: None, reward: 1.86577613703
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.8657761370334645, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.87)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: forward, reward: 1.11322841766
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.1132284176609188, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.11)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: forward, reward: 1.03584573002
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': 1.0358457300210362, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.04)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: None, reward: 1.52810376062
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.5281037606197732, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.53)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: left, reward: 0.502769631074
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 0.5027696310740717, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.50)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 1.28223166757
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.2822316675681686, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.28)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 0.840876996619
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.8408769966189023, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.84)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 0.328346531699
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.32834653169926664, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.33)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 161
\-------------------------

Environment.reset(): Trial set up with start = (5, 6), destination = (8, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0894; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0894; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: right, reward: 2.39139365052
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.3913936505194178, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.39)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: forward, reward: 2.52706215691
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 2.5270621569094214, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.53)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 0.558888766099
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.5588887660992806, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.56)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: left, reward: 2.55072075423
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 2.550720754234282, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.55)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 0.983595175461
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 0.9835951754607439, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.98)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: left, reward: 2.0502692715
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.0502692714972337, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.05)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 1.87967392548
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.8796739254752544, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.88)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: forward, reward: 1.4707896136
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.470789613596352, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.47)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 162
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (8, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0880; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: 1.24685824442
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.2468582444210359, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.25)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: right, reward: 2.16536111295
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 2.1653611129478487, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.17)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: forward, reward: 2.2551856187
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': 2.255185618698671, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.26)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: None, reward: 1.87132049436
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.8713204943550978, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.87)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: left, reward: 1.48353131608
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.4835313160817032, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.48)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: right, reward: 2.40000961596
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 2.400009615957452, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.40)
76% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 163
\-------------------------

Environment.reset(): Trial set up with start = (3, 6), destination = (1, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0867; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 2.57078483499
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.570784834994746, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.57)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 2.28683672806
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.286836728060356, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.29)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.71026119142
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.7102611914198231, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.71)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.87428223494
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.8742822349437331, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.87)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: left, reward: 2.11625351778
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 2.1162535177816615, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.12)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.19888500562
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.1988850056227027, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.20)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: right, reward: 0.344681882689
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.3446818826891975, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.34)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: left, reward: 2.69655807559
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 2.6965580755934635, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.70)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: right, reward: 2.22275831428
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.2227583142794636, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.22)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 164
\-------------------------

Environment.reset(): Trial set up with start = (5, 6), destination = (8, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0854; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: left, reward: -40.9419001443
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 4, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 25, 't': 0, 'action': 'left', 'reward': -40.94190014427212, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -40.94)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: right, reward: 1.6298276528
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'right'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.629827652798392, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'right')
Agent drove right instead of left. (rewarded 1.63)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: right, reward: 1.52925050795
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.5292505079511107, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.53)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 2.178763283
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.1787632830007144, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.18)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 2.71349577293
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.7134957729348512, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.71)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: None, reward: 2.90665821985
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.906658219846192, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.91)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: forward, reward: 2.02145969775
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.021459697751421, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.02)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 2.29435899566
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.2943589956628494, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.29)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 2.14467673526
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.144676735263893, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 1.59704669305
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.5970466930521585, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.60)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 2.48845210561
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 2.4884521056122946, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.49)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: right, reward: 1.03599457171
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.0359945717081214, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.04)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: left, reward: 1.73848829522
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 1.7384882952210796, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.74)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: right, reward: 2.41250257662
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 2.412502576623872, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.41)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: left, reward: -9.33535982957
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 11, 't': 14, 'action': 'left', 'reward': -9.335359829568645, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -9.34)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: None, reward: 1.16987710562
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 10, 't': 15, 'action': None, 'reward': 1.1698771056211377, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.17)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: right, reward: 0.895844080612
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 0.8958440806122937, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.90)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: -10.9411211506
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 8, 't': 17, 'action': 'forward', 'reward': -10.941121150635446, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.94)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: None, reward: 1.24884366594
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.248843665939037, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.25)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: -9.82971582687
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': -9.829715826873988, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent attempted driving forward through a red light. (rewarded -9.83)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: -10.942324681
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 20, 'action': 'forward', 'reward': -10.942324680954606, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.94)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: left, reward: 1.04342795413
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 4, 't': 21, 'action': 'left', 'reward': 1.0434279541330822, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.04)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 0.463333717523
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 3, 't': 22, 'action': None, 'reward': 0.4633337175234198, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.46)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 1.81543470932
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 2, 't': 23, 'action': None, 'reward': 1.8154347093186707, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.82)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 0.874359176734
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 1, 't': 24, 'action': None, 'reward': 0.8743591767340311, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.87)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 165
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (6, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0842; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0842; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: forward, reward: 0.62994335198
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 0.6299433519800666, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 0.63)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: left, reward: 1.56860575916
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.5686057591637672, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.57)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: 2.27769783149
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 2.277697831489289, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.28)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: right, reward: 1.18975987829
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.189759878292721, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 1.19)
80% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 166
\-------------------------

Environment.reset(): Trial set up with start = (6, 7), destination = (1, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0829; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: 1.61986388207
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 1.6198638820676292, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.62)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: right, reward: 0.268682389528
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 0.2686823895278647, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.27)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 1.94422060434
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.9442206043361467, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.94)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 1.87990822116
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.8799082211607487, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.88)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: left, reward: 2.61933427632
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 2.619334276315107, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.62)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 1.83206949837
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.8320694983690897, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.83)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 1.54245690943
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.5424569094343479, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.54)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 0.910465146297
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 7, 'action': None, 'reward': 0.9104651462968063, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.91)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 2.77375616915
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.77375616915125, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.77)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 0.221525173189
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 0.22152517318883946, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.22)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: left, reward: 1.0378731565
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 1.0378731565003032, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.04)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 1.46271339116
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.4627133911647057, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.46)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: 1.28765167737
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 1.2876516773651205, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 1.29)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 1.47475768351
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 1.4747576835133627, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.47)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 0.953251660506
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 11, 't': 14, 'action': 'left', 'reward': 0.9532516605062026, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.95)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: right, reward: 2.15197367833
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 2.1519736783273817, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.15)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: right, reward: -20.3508670793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 9, 't': 16, 'action': 'right', 'reward': -20.350867079340365, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.35)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: right, reward: 1.9069720199
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 8, 't': 17, 'action': 'right', 'reward': 1.906972019904961, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.91)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 0.994933022918
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 18, 'action': 'forward', 'reward': 0.9949330229176192, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.99)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: -4.83585773533
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 6, 't': 19, 'action': None, 'reward': -4.8358577353257735, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.84)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: forward, reward: 0.763909951828
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 5, 't': 20, 'action': 'forward', 'reward': 0.7639099518280645, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent drove forward instead of right. (rewarded 0.76)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 1.13042244568
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 4, 't': 21, 'action': 'right', 'reward': 1.13042244568015, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.13)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: right, reward: 1.81293043103
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 3, 't': 22, 'action': 'right', 'reward': 1.8129304310313579, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.81)
8% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 167
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (4, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0817; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: left, reward: 2.91501846105
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.915018461046577, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.92)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: left, reward: 2.26212245724
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 2.2621224572411642, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.26)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 2.38715807031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.3871580703071396, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.39)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 1.01625381114
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0162538111389567, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.02)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: forward, reward: 1.2500120865
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.2500120864979047, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.25)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: forward, reward: 1.09109243646
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.091092436460588, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.09)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 168
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (1, 2), deadline = 30
Simulating trial. . . 
epsilon = 0.0805; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0805; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 1.65427727007
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.6542772700708603, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.65)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 2.84937070514
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 29, 't': 1, 'action': None, 'reward': 2.849370705140381, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.85)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 1.31899651206
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.3189965120636287, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.32)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 1.3480386484
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.348038648395383, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.35)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: left, reward: 2.01831120257
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 26, 't': 4, 'action': 'left', 'reward': 2.018311202566551, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.02)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.61774796854
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 25, 't': 5, 'action': None, 'reward': 2.6177479685361797, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.62)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.28132738146
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 24, 't': 6, 'action': None, 'reward': 1.2813273814621728, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.28)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.71313323104
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.7131332310408303, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.71)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.65065979031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.6506597903060163, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.65)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: 2.42416342769
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 2.4241634276920685, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.42)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 2.45326111203
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 2.453261112033099, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.45)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 1.77594646235
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 1.7759464623533332, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.78)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 2.48070212269
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.4807021226898778, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.48)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: 1.53299223222
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 1.5329922322187133, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.53)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: forward, reward: 1.61041980311
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 14, 'action': 'forward', 'reward': 1.6104198031067711, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.61)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: None, reward: 2.42179086254
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 15, 't': 15, 'action': None, 'reward': 2.421790862539501, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.42)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: None, reward: 1.44872065934
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.4487206593411377, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.45)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: forward, reward: 1.2023344789
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 17, 'action': 'forward', 'reward': 1.2023344788966919, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.20)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 169
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (1, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0793; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0793; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: right, reward: 1.38087954962
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.3808795496193682, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.38)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 1.80229192355
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.802291923551424, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.80)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: forward, reward: 0.337779314795
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': 0.3377793147946282, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.34)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 1.12835952387
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.1283595238727149, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.13)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 2.16039176798
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.160391767977295, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.16)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 2.09790191047
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.0979019104705285, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.10)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: left, reward: 2.85974266537
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 2.8597426653682634, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.86)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: forward, reward: 1.23376169014
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.233761690135159, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 1.23)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: 2.09682973387
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 2.096829733865328, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.10)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 1.19108761057
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.1910876105731691, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.19)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: left, reward: 1.81962713302
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 1.819627133016682, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.82)
56% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 170
\-------------------------

Environment.reset(): Trial set up with start = (1, 4), destination = (6, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0781; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: forward, reward: 1.84337536867
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.8433753686677983, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 1.84)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: left, reward: 1.85002384913
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.8500238491306322, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.85)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: -4.04526373912
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': -4.045263739120433, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -4.05)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: 1.21877232489
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.2187723248929558, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.22)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: right, reward: 1.72757534182
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.7275753418167317, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.73)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 1.08998366183
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.0899836618347722, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.09)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: left, reward: 1.68193176056
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.6819317605599289, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.68)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 0.109582871491
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.10958287149098367, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.11)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 2.34905830416
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.349058304161491, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.35)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: left, reward: 2.40050222394
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.4005022239441436, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.40)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.755303381
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.7553033809962362, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.76)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 0.999958917935
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 9, 't': 11, 'action': None, 'reward': 0.9999589179351112, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.00)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 0.99209010493
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 0.9920901049304722, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.99)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: forward, reward: 2.36442692062
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 2.364426920616618, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.36)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: right, reward: 0.591483018099
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 0.5914830180992499, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.59)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: 0.816550141871
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 5, 't': 15, 'action': None, 'reward': 0.8165501418711298, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.82)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: forward, reward: 1.30479685161
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 1.304796851610095, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.30)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: right, reward: 0.319443842641
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 0.3194438426406513, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.32)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: left, reward: 0.741900556795
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 2, 't': 18, 'action': 'left', 'reward': 0.7419005567952899, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.74)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: None, reward: 1.24728596593
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.247285965925677, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.25)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 171
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (5, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0769; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: left, reward: 1.85467990263
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 25, 't': 0, 'action': 'left', 'reward': 1.8546799026346836, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.85)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: None, reward: 1.4931014716
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.4931014715986783, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.49)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: None, reward: 1.26457097464
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.2645709746381861, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.26)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: None, reward: 2.25645239099
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.2564523909930774, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.26)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: forward, reward: 1.99867635815
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.9986763581491027, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.00)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: right, reward: 1.60007620627
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 1.6000762062745237, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.60)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: -4.24688492651
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 19, 't': 6, 'action': None, 'reward': -4.246884926512424, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -4.25)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: 2.56892501825
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.568925018245772, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.57)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: 1.45728130865
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.4572813086498921, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.46)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: 1.76821411617
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.7682141161650986, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.77)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: forward, reward: 1.56036671748
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.560366717475866, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.56)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: right, reward: -0.179599164378
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': -0.17959916437788082, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded -0.18)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 2.41693021699
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 2.4169302169937423, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.42)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 2.61736158508
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 2.6173615850798093, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.62)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: forward, reward: 2.58855695528
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 14, 'action': 'forward', 'reward': 2.58855695528437, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.59)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: forward, reward: 0.756761786158
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 0.7567617861583262, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent drove forward instead of right. (rewarded 0.76)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: right, reward: 0.810569583805
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 0.8105695838048259, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.81)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: right, reward: 1.75137793358
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 8, 't': 17, 'action': 'right', 'reward': 1.7513779335779474, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.75)
28% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 172
\-------------------------

Environment.reset(): Trial set up with start = (2, 2), destination = (6, 5), deadline = 35
Simulating trial. . . 
epsilon = 0.0758; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: None, reward: 2.07640985327
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 35, 't': 0, 'action': None, 'reward': 2.076409853269967, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.08)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: right, reward: 0.448879880519
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 34, 't': 1, 'action': 'right', 'reward': 0.4488798805192644, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.45)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: 1.4433526874
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 33, 't': 2, 'action': 'forward', 'reward': 1.443352687402589, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.44)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: 1.82025393906
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 32, 't': 3, 'action': 'right', 'reward': 1.820253939058717, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.82)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 1.59394015715
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 31, 't': 4, 'action': None, 'reward': 1.593940157153468, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.59)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 1.17020161621
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 30, 't': 5, 'action': None, 'reward': 1.1702016162056343, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.17)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 2.66510494676
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 29, 't': 6, 'action': None, 'reward': 2.665104946758383, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.67)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: right, reward: 1.21306409142
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 28, 't': 7, 'action': 'right', 'reward': 1.2130640914230204, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.21)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 1.24226653348
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 27, 't': 8, 'action': None, 'reward': 1.2422665334777274, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.24)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: left, reward: 1.75621129028
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 26, 't': 9, 'action': 'left', 'reward': 1.7562112902805955, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.76)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: left, reward: 1.50957618357
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 25, 't': 10, 'action': 'left', 'reward': 1.509576183568287, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.51)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: forward, reward: 2.87759301801
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 24, 't': 11, 'action': 'forward', 'reward': 2.877593018013493, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.88)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 1.57711116263
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 12, 'action': None, 'reward': 1.5771111626264145, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.58)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: forward, reward: 1.72685182527
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 22, 't': 13, 'action': 'forward', 'reward': 1.726851825274825, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.73)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: forward, reward: -10.5376810222
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 21, 't': 14, 'action': 'forward', 'reward': -10.537681022244653, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent attempted driving forward through a red light. (rewarded -10.54)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: right, reward: 2.63349245051
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 20, 't': 15, 'action': 'right', 'reward': 2.633492450507669, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.63)
54% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 173
\-------------------------

Environment.reset(): Trial set up with start = (5, 2), destination = (7, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0746; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: right, reward: 1.8570581382
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.857058138200712, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 1.86)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: forward, reward: 2.65291288244
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 2.652912882444095, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.65)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: left, reward: 2.11220488212
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 2.112204882119334, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.11)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: forward, reward: 2.56964974172
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.5696497417236888, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.57)
80% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 174
\-------------------------

Environment.reset(): Trial set up with start = (4, 7), destination = (1, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0735; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: forward, reward: 1.05164934413
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.0516493441334234, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.05)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: None, reward: 1.51406587286
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.514065872858487, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.51)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: 0.808317373204
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.8083173732040946, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.81)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: left, reward: 1.8232165629
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.8232165629001358, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.82)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: forward, reward: 0.982787155255
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 0.9827871552545604, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.98)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: forward, reward: 1.83372644966
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.8337264496592887, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.83)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: forward, reward: 1.19084068481
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.1908406848134065, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.19)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: forward, reward: 0.289968942234
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 0.2899689422344318, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent drove forward instead of left. (rewarded 0.29)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: 1.52083141022
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.5208314102189762, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.52)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: right, reward: 1.0814474958
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.081447495795452, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.08)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: left, reward: 0.365637398437
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 0.36563739843694754, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.37)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: right, reward: 1.70839774506
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.7083977450586378, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 1.71)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: forward, reward: 1.33733608944
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'right'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 1.337336089444789, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'right')
Agent drove forward instead of right. (rewarded 1.34)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 2.44227126521
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 2.442271265210713, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.44)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 1.34234179465
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': 1.342341794645913, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.34)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 2.00966849322
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.009668493216008, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.01)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: None, reward: 2.11880500989
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 4, 't': 16, 'action': None, 'reward': 2.1188050098876126, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.12)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: 2.23499991341
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'left', 'reward': 2.234999913413781, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.23)
10% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 175
\-------------------------

Environment.reset(): Trial set up with start = (8, 7), destination = (5, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0724; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 1.64893816807
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.6489381680662432, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.65)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 1.39294361623
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.392943616230024, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.39)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 1.58872157113
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.5887215711283027, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.59)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 2.19369739772
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.1936973977167287, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.19)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: None, reward: 0.99135401674
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 0.9913540167396584, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.99)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: left, reward: 1.94629576469
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 1.9462957646856378, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.95)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: right, reward: 0.571546793809
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 0.5715467938093183, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.57)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: left, reward: 2.02496074413
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 2.024960744128202, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.02)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 1.14041442442
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 1.1404144244227084, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.14)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: right, reward: 2.31071127464
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 2.3107112746422085, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.31)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 176
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (7, 6), deadline = 30
Simulating trial. . . 
epsilon = 0.0714; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0714; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0714; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 2.12658769092
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 30, 't': 0, 'action': 'right', 'reward': 2.1265876909228925, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.13)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 1.54794193245
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.5479419324549548, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.55)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 2.04776499942
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 28, 't': 2, 'action': None, 'reward': 2.0477649994153673, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.05)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 2.57028132192
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 2.5702813219154006, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.57)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: -9.23362837136
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': -9.233628371362569, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent attempted driving forward through a red light. (rewarded -9.23)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: right, reward: 0.135044668447
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.13504466844742746, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.14)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: right, reward: 1.90673126438
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'right'), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.9067312643796113, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'right')
Agent drove right instead of left. (rewarded 1.91)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 0.984973196635
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 0.9849731966354465, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 0.98)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 2.27057656321
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 2.2705765632146706, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.27)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.26009413114
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 21, 't': 9, 'action': None, 'reward': 1.2600941311360465, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.26)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 2.31863641227
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': 2.3186364122677805, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.32)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.10127142954
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 1.1012714295382235, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.10)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.53064843146
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.5306484314579596, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.53)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 1.14797176001
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 1.1479717600143555, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.15)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: right, reward: 0.608273068156
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 0.6082730681556918, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.61)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: forward, reward: 0.998875467135
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 15, 't': 15, 'action': 'forward', 'reward': 0.9988754671349817, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent drove forward instead of left. (rewarded 1.00)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: None, reward: 0.914196772965
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 0.9141967729651967, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.91)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: right, reward: 1.70020462407
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 1.7002046240702777, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.70)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: 1.3802560031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 12, 't': 18, 'action': None, 'reward': 1.3802560030953743, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.38)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: forward, reward: 0.676157898595
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': 0.6761578985951996, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.68)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 1.46369609261
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.4636960926122706, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.46)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: right, reward: 0.565183791233
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 9, 't': 21, 'action': 'right', 'reward': 0.5651837912325984, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.57)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: right, reward: 0.627887791842
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'right'), 'deadline': 8, 't': 22, 'action': 'right', 'reward': 0.6278877918422567, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'right')
Agent followed the waypoint right. (rewarded 0.63)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: right, reward: -0.469434745892
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 7, 't': 23, 'action': 'right', 'reward': -0.469434745892105, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent drove right instead of forward. (rewarded -0.47)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: None, reward: 0.540125058443
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 24, 'action': None, 'reward': 0.5401250584427904, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.54)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: left, reward: 1.80449384614
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 25, 'action': 'left', 'reward': 1.8044938461359352, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.80)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 1.18535507285
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 4, 't': 26, 'action': None, 'reward': 1.1853550728546487, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.19)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 0.335134329367
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 3, 't': 27, 'action': None, 'reward': 0.33513432936699084, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.34)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 1.11622139033
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 2, 't': 28, 'action': 'right', 'reward': 1.116221390329089, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.12)
3% of time remaining to reach destination.

/-------------------
| Step 29 Results
\-------------------

Environment.step(): t = 29
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: 1.62177594294
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'forward'), 'deadline': 1, 't': 29, 'action': None, 'reward': 1.6217759429421226, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.62)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 177
\-------------------------

Environment.reset(): Trial set up with start = (6, 3), destination = (5, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0703; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 1.08586946585
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.0858694658544321, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.09)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: 1.32350950091
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.3235095009089815, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.32)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: left, reward: 0.848982935054
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 0.8489829350541297, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.85)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: forward, reward: 2.56751300449
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.567513004486939, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.57)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: forward, reward: 2.05032943143
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.050329431425837, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.05)
75% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 178
\-------------------------

Environment.reset(): Trial set up with start = (6, 5), destination = (4, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0693; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: right, reward: 1.66904282031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.6690428203088592, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.67)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: left, reward: 1.94090585144
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 24, 't': 1, 'action': 'left', 'reward': 1.9409058514425164, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.94)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 1.66464399301
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.6646439930125758, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.66)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: right, reward: 2.53900031584
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 2.5390003158387304, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.54)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: forward, reward: 2.20784795294
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 2.2078479529355386, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.21)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: forward, reward: 1.22372079098
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 1.2237207909819767, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.22)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 2), heading: (0, 1), action: left, reward: 2.55367489949
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 2.5536748994907206, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.55)
72% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 179
\-------------------------

Environment.reset(): Trial set up with start = (8, 2), destination = (6, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0682; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: forward, reward: 1.0541546651
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.0541546651018807, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.05)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: left, reward: 1.788125246
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.7881252460029924, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.79)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: None, reward: 2.59913546263
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.599135462630772, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.60)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: left, reward: 2.53161357216
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 2.5316135721595128, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.53)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: None, reward: 1.18702916158
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.187029161575833, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.19)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: 2.54969593924
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.549695939244443, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.55)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: forward, reward: 1.18157538906
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.1815753890565888, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.18)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: None, reward: -0.103881324479
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': -0.10388132447917031, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded -0.10)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: right, reward: 1.62656542456
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.6265654245619223, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.63)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 180
\-------------------------

Environment.reset(): Trial set up with start = (8, 7), destination = (6, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0672; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: left, reward: 1.0235424688
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 1.0235424687991694, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.02)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: forward, reward: 2.03707974128
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 2.0370797412816426, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.04)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: right, reward: 1.73863280614
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.7386328061410596, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.74)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 2.1685937356
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 2.1685937355952034, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.17)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: None, reward: 1.15470112286
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.1547011228628397, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.15)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 1.62235271434
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.6223527143396057, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.62)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: forward, reward: 0.721603347762
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.721603347762122, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 0.72)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 1.2193646961
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.2193646961033389, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.22)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 2.66665552006
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.666655520057619, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.67)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: None, reward: 2.41892843389
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.418928433887709, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.42)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: -0.0905160296662
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': -0.09051602966621297, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded -0.09)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 0.0643070255259
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'forward'), 'deadline': 9, 't': 11, 'action': None, 'reward': 0.06430702552589085, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 0.06)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 0.950827332156
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.9508273321559757, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.95)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: right, reward: 2.34531953817
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 2.345319538169745, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.35)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 1.37548969095
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.3754896909506809, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.38)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 1.35778592542
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 1.3577859254197555, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.36)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 0.545145504151
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 4, 't': 16, 'action': None, 'reward': 0.5451455041508393, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.55)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 2.09194018124
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 2.091940181244704, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.09)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: left, reward: -39.2260049528
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 4, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 2, 't': 18, 'action': 'left', 'reward': -39.22600495282313, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent attempted driving left through a red light with traffic and cause a major accident. (rewarded -39.23)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 0.393770258858
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.39377025885760364, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'red', 'forward', None)
Agent properly idled at a red light. (rewarded 0.39)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 181
\-------------------------

Environment.reset(): Trial set up with start = (1, 3), destination = (7, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0662; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0662; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0662; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0662; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 1.48831517165
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.488315171645162, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.49)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.50796253493
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.507962534928983, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.51)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 1.5043894075
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.5043894075048292, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.50)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.82410058961
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.8241005896133307, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.82)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: -4.52232701166
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': -4.522327011659731, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.52)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: forward, reward: 2.4930849164
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.4930849163954782, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.49)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: 2.03629873014
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.036298730137937, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.04)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 1.18437097086
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.184370970857158, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.18)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: forward, reward: 2.63454617752
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 2.6345461775174304, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.63)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 182
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (7, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.0652; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0652; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0652; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: -4.22302952236
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 1, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 30, 't': 0, 'action': None, 'reward': -4.223029522360316, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.22)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: left, reward: 1.56955690561
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 29, 't': 1, 'action': 'left', 'reward': 1.5695569056138234, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.57)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: right, reward: 1.98109957663
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.981099576633154, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 1.98)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 1.68938438478
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.689384384775993, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.69)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 2.43015419832
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 26, 't': 4, 'action': None, 'reward': 2.4301541983156913, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.43)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: right, reward: 0.545795487971
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 25, 't': 5, 'action': 'right', 'reward': 0.5457954879706278, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.55)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: right, reward: 1.8341859344
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.8341859343977274, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.83)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 2.63271318531
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 2.6327131853050254, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.63)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 1.0044820477
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.0044820477000516, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 2.77681473017
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 9, 'action': None, 'reward': 2.776814730171159, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.78)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 2.2365893418
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 10, 'action': None, 'reward': 2.2365893417951606, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.24)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: forward, reward: 2.53760158509
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'forward', 'reward': 2.537601585089031, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.54)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 2.52031515694
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.5203151569380853, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.52)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: right, reward: 1.16498999503
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 1.1649899950303808, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.16)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: 1.37710878728
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 1.377108787281491, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.38)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: 2.02272911365
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 15, 'action': 'forward', 'reward': 2.022729113646616, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.02)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 0.925505312023
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 14, 't': 16, 'action': 'forward', 'reward': 0.925505312022842, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 0.93)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 1.93517193061
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 1.935171930610967, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.94)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: 0.87890231045
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 12, 't': 18, 'action': None, 'reward': 0.8789023104500726, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.88)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: right, reward: 1.0294439497
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 11, 't': 19, 'action': 'right', 'reward': 1.0294439496979801, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.03)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 1.2391743996
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.2391743996033298, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.24)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 1.45285878525
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 21, 'action': None, 'reward': 1.452858785254485, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.45)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: right, reward: 1.23462203863
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 8, 't': 22, 'action': 'right', 'reward': 1.2346220386268862, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.23)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: right, reward: 2.20976368353
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 2.209763683530543, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.21)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 1.05558690081
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 6, 't': 24, 'action': 'right', 'reward': 1.0555869008076553, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.06)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: right, reward: 1.5120544424
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 1.512054442398056, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.51)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: None, reward: 0.755612410188
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 4, 't': 26, 'action': None, 'reward': 0.7556124101880397, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.76)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: right, reward: -19.3066789465
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 3, 't': 27, 'action': 'right', 'reward': -19.30667894645323, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -19.31)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: left, reward: 0.582444513815
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 2, 't': 28, 'action': 'left', 'reward': 0.5824445138154666, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.58)
3% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 183
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (6, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0642; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: left, reward: 1.22554957209
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 1.225549572086162, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.23)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 2.07416766813
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.074167668127785, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.07)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 2.01209712698
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.0120971269847967, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.01)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: left, reward: 1.81508340852
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.8150834085197487, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.82)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.42351107782
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.423511077823718, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 1.42)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 2.49153841034
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.4915384103406377, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.49)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 2.0342728002
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.0342728002032757, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.03)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: forward, reward: 2.2263720139
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.226372013904326, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.23)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: right, reward: 2.05255312419
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.052553124192435, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.05)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 184
\-------------------------

Environment.reset(): Trial set up with start = (8, 3), destination = (2, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0633; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0633; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0633; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0633; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: -19.4230639108
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 3, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': -19.42306391083347, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent attempted driving left through traffic and cause a minor accident. (rewarded -19.42)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 2.91798699077
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.9179869907671074, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.92)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: 2.75771415411
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.757714154108428, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.76)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: right, reward: 0.371014930895
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.37101493089497517, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.37)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: left, reward: 0.998068462549
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 0.9980684625491136, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.00)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: 1.01708971457
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.0170897145670346, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.02)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: None, reward: 1.4086838553
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.4086838552959138, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.41)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 4), heading: (0, 1), action: right, reward: 0.621412563165
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.6214125631648941, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.62)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: right, reward: 1.60890627172
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.608906271721116, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.61)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: right, reward: 0.96448762953
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 0.9644876295304807, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 0.96)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: right, reward: 2.25803140481
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 2.258031404808455, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.26)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: left, reward: 0.941572411032
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 0.9415724110316719, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.94)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: forward, reward: 1.82153526129
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 1.8215352612900422, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.82)
35% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 185
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (3, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0623; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: left, reward: 2.82777231146
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.827772311460806, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.83)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: None, reward: 2.12847825178
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.128478251784799, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.13)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: forward, reward: -9.7358200381
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': -9.735820038096676, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -9.74)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: right, reward: 0.944237645963
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.9442376459633356, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent drove right instead of left. (rewarded 0.94)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: None, reward: 2.3051263526
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.3051263526001846, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.31)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: None, reward: 2.50158989078
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.501589890780386, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.50)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: None, reward: 1.40825813724
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.4082581372430163, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.41)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: left, reward: 1.57710285601
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.577102856011695, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.58)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 2.47356310957
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.4735631095723045, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.47)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 2.15725275201
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.1572527520108915, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.16)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 1.52447421889
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.5244742188944995, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.52)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: forward, reward: 1.12551802936
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 1.125518029364199, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.13)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 2.57060779713
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 2.570607797131638, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.57)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: 1.97485832785
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.9748583278463432, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.97)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 1.04114667633
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.0411466763339385, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.04)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: forward, reward: 0.775094595686
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'forward', 'reward': 0.7750945956863486, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.78)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: forward, reward: 0.44981991119
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 0.4498199111896444, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.45)
15% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 186
\-------------------------

Environment.reset(): Trial set up with start = (7, 2), destination = (4, 5), deadline = 30
Simulating trial. . . 
epsilon = 0.0614; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0614; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 2.66038201967
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 30, 't': 0, 'action': None, 'reward': 2.6603820196650902, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.66)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.90183045457
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 29, 't': 1, 'action': None, 'reward': 1.9018304545698959, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.90)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.24368985118
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.243689851181705, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.24)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: left, reward: -10.9144724807
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': 'left', 'reward': -10.914472480690666, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent attempted driving left through a red light. (rewarded -10.91)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: 1.32897388104
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 1.3289738810407041, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.33)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: forward, reward: 1.79309335338
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 1.7930933533828397, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.79)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: None, reward: 2.84339482739
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 6, 'action': None, 'reward': 2.843394827392009, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.84)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: None, reward: 2.8607965578
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 23, 't': 7, 'action': None, 'reward': 2.8607965578013324, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.86)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: None, reward: 1.72820835473
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.7282083547286264, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.73)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 1.50693129319
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 1.506931293187499, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.51)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 2.46678047651
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 20, 't': 10, 'action': None, 'reward': 2.466780476511722, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.47)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: right, reward: 0.90233948864
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 0.9023394886398032, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.90)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: left, reward: 1.65838193443
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 12, 'action': 'left', 'reward': 1.658381934433685, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.66)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 0.558791566893
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 17, 't': 13, 'action': 'right', 'reward': 0.5587915668925718, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 0.56)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: left, reward: 2.42503716282
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 2.4250371628238065, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.43)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: left, reward: 2.24476586223
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 15, 't': 15, 'action': 'left', 'reward': 2.2447658622291335, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.24)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.66333358835
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.663333588354686, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.66)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.95501608593
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 13, 't': 17, 'action': None, 'reward': 1.9550160859251007, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.96)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.86734353508
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 18, 'action': None, 'reward': 1.8673435350781262, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.87)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 0.725114258686
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 19, 'action': None, 'reward': 0.7251142586857644, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.73)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 2.57297022751
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 10, 't': 20, 'action': None, 'reward': 2.57297022750883, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.57)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: forward, reward: 1.59484451073
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'forward', 'reward': 1.5948445107315383, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.59)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: right, reward: -0.242891368532
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 8, 't': 22, 'action': 'right', 'reward': -0.24289136853161297, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded -0.24)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: right, reward: 1.24641821865
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 7, 't': 23, 'action': 'right', 'reward': 1.2464182186462591, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.25)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: right, reward: 2.1896079375
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 6, 't': 24, 'action': 'right', 'reward': 2.189607937500752, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.19)
17% of time remaining to reach destination.

/-------------------
| Step 25 Results
\-------------------

Environment.step(): t = 25
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: right, reward: 1.28692883726
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 5, 't': 25, 'action': 'right', 'reward': 1.2869288372603802, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.29)
13% of time remaining to reach destination.

/-------------------
| Step 26 Results
\-------------------

Environment.step(): t = 26
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 1.25664730686
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 4, 't': 26, 'action': None, 'reward': 1.2566473068577617, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.26)
10% of time remaining to reach destination.

/-------------------
| Step 27 Results
\-------------------

Environment.step(): t = 27
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 0.750273522483
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 3, 't': 27, 'action': None, 'reward': 0.7502735224827983, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.75)
7% of time remaining to reach destination.

/-------------------
| Step 28 Results
\-------------------

Environment.step(): t = 28
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: forward, reward: 0.18163173209
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 2, 't': 28, 'action': 'forward', 'reward': 0.18163173209003158, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.18)
3% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 187
\-------------------------

Environment.reset(): Trial set up with start = (6, 5), destination = (2, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0605; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: forward, reward: 0.208545468365
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 0.20854546836531096, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'forward')
Agent drove forward instead of left. (rewarded 0.21)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: None, reward: 1.89286171341
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.8928617134124108, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.89)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: None, reward: 1.13284528723
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.13284528722811, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.13)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: None, reward: 2.05894134356
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.0589413435579553, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.06)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: left, reward: 1.93473846402
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.9347384640157241, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.93)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: forward, reward: 2.72489095627
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.7248909562673846, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.72)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: forward, reward: 2.35355239442
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.353552394415864, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.35)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: forward, reward: 2.15125184387
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.1512518438714423, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.15)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: -0.0375463882922
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': -0.03754638829217838, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent drove forward instead of left. (rewarded -0.04)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 2.65476631994
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.6547663199396245, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.65)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: left, reward: 2.09979519413
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.0997951941251656, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.10)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: left, reward: 1.61055072751
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.6105507275087263, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.61)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 188
\-------------------------

Environment.reset(): Trial set up with start = (1, 3), destination = (3, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0596; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: left, reward: 1.51885726286
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'left', 'reward': 1.5188572628595727, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.52)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: forward, reward: 1.30511254965
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': 1.3051125496469995, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.31)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 1.61643023611
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.6164302361094847, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.62)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: left, reward: 1.67387642196
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 1.673876421964728, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.67)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 2.37117214314
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.3711721431425463, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.37)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 1.100591458
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 1.1005914580011442, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.10)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: 1.43392695432
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'right'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.433926954318364, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.43)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: None, reward: 2.42338931676
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.423389316760845, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.42)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: -0.109362469633
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 17, 't': 8, 'action': 'right', 'reward': -0.10936246963318641, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded -0.11)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: right, reward: 1.71525031743
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 1.715250317433865, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.72)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: -10.1938186137
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': -10.193818613673606, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent attempted driving forward through a red light. (rewarded -10.19)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.45857208759
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.4585720875899735, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.46)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 1.34866713809
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.3486671380861766, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.35)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 0.980610208605
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 12, 't': 13, 'action': None, 'reward': 0.9806102086051502, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 0.98)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 1.03821566514
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.0382156651372723, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.04)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 2.58935588584
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 15, 'action': None, 'reward': 2.58935588584021, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.59)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 1.09404755535
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 1.0940475553519833, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.09)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: left, reward: 1.31407435854
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 8, 't': 17, 'action': 'left', 'reward': 1.3140743585384056, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.31)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: left, reward: 2.30656371743
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 7, 't': 18, 'action': 'left', 'reward': 2.3065637174269833, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.31)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: None, reward: -0.323930991873
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 6, 't': 19, 'action': None, 'reward': -0.32393099187275365, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded -0.32)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: right, reward: 1.25709629916
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 5, 't': 20, 'action': 'right', 'reward': 1.2570962991624954, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 1.26)
16% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 189
\-------------------------

Environment.reset(): Trial set up with start = (5, 4), destination = (2, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0587; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 1.31248708936
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.312487089362496, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.31)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: right, reward: 0.366835527658
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.3668355276582257, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.37)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: right, reward: 1.25490216669
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.254902166685904, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.25)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: right, reward: 1.83408658969
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.8340865896927472, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.83)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: -10.059645892
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': -10.059645892008316, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent attempted driving forward through a red light. (rewarded -10.06)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: None, reward: 2.18739564791
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.18739564790514, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.19)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: right, reward: 0.869818740923
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.8698187409234759, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.87)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: forward, reward: 1.15972293744
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.1597229374426623, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent drove forward instead of left. (rewarded 1.16)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: forward, reward: 2.358278337
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 2.3582783370012956, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.36)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: 2.34234010494
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.342340104941642, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.34)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: 2.1095509801
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.1095509800963574, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.11)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: forward, reward: 0.848545773782
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 0.8485457737821733, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.85)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: forward, reward: 1.5876344029
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 1.5876344029030693, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.59)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: right, reward: 1.01069467486
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 1.0106946748615981, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.01)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: None, reward: 1.72384149565
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.7238414956483272, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.72)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: None, reward: 2.45259583089
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.452595830889254, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.45)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: None, reward: 2.25717101561
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': None, 'reward': 2.257171015608809, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.26)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: left, reward: 0.96150265265
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'left', 'reward': 0.9615026526502526, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 0.96)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: right, reward: 0.411702248218
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 0.4117022482181958, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 0.41)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: forward, reward: 0.402280513162
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': 0.4022805131621465, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.40)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 190
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (5, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0578; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0578; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0578; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: forward, reward: 1.17706113793
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.1770611379292764, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.18)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: right, reward: 1.18731892606
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.1873189260590293, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.19)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: 1.70510869982
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.7051086998248421, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.71)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: right, reward: 1.52299597076
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.5229959707572838, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.52)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: right, reward: 1.30547663655
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.3054766365469932, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.31)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: None, reward: 1.85768535928
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.8576853592799, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.86)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: forward, reward: 2.20709784209
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'right'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.2070978420913, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'right')
Agent followed the waypoint forward. (rewarded 2.21)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: forward, reward: -9.77167577976
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': -9.771675779761157, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent attempted driving forward through a red light. (rewarded -9.77)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 0.962420089641
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 12, 't': 8, 'action': None, 'reward': 0.9624200896411688, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.96)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 1.49324424098
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.4932442409757436, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.49)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: None, reward: 0.983989468135
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 0.9839894681347487, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.98)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: forward, reward: 1.57691657294
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 1.576916572940503, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.58)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: right, reward: 2.18499541839
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 2.184995418393865, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.18)
35% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 191
\-------------------------

Environment.reset(): Trial set up with start = (1, 5), destination = (4, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.0570; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 1.67881778165
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.6788177816498353, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.68)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 1.65974404122
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.6597440412160487, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.66)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: 2.18795466524
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 2.187954665237819, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.19)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 2.59988091053
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.5998809105307084, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.60)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.23852140486
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.2385214048596247, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.24)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: 1.70367393701
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 1.7036739370054068, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent drove left instead of forward. (rewarded 1.70)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: 1.76702439686
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.7670243968582926, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.77)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: 0.658556452201
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 18, 't': 7, 'action': None, 'reward': 0.6585564522011869, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.66)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: right, reward: 2.802100745
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 2.802100744998187, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.80)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: forward, reward: 1.90482312711
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 1.9048231271092633, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.90)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: right, reward: 0.396236848553
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 0.396236848553324, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 0.40)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: 2.41049603024
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 14, 't': 11, 'action': None, 'reward': 2.4104960302391936, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.41)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: None, reward: 1.10716592299
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.1071659229933826, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.11)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: forward, reward: 0.818127911235
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 0.8181279112347482, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.82)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 0.83895249868
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 0.8389524986795713, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.84)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: forward, reward: 2.2127290746
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 2.2127290745989225, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.21)
36% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 192
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (3, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0561; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 1.50444620183
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.504446201828292, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.50)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 2.02693880745
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': 2.026938807453395, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.03)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 2.44616101117
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 2.4461610111667724, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.45)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 1.26059827539
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.260598275389797, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.26)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 1.80826372933
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.8082637293330435, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.81)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 1.59159325301
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.5915932530073555, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.59)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: forward, reward: 2.87112812708
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.8711281270750715, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.87)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 2.89582053487
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.895820534874512, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.90)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 0.891916544621
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 0.891916544620589, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.89)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 2.30965879147
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 9, 'action': None, 'reward': 2.3096587914668056, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.31)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: left, reward: 1.34498184574
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 1.3449818457350333, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 1.34)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: right, reward: 2.1531476167
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'left'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 2.1531476166996537, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'left')
Agent followed the waypoint right. (rewarded 2.15)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: right, reward: 2.74645359112
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 2.746453591118996, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.75)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 193
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (8, 5), deadline = 35
Simulating trial. . . 
epsilon = 0.0553; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 1.41290886381
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 35, 't': 0, 'action': None, 'reward': 1.4129088638123315, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.41)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 0.604215578031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 34, 't': 1, 'action': 'right', 'reward': 0.6042155780312515, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.60)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 2.58170019318
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 33, 't': 2, 'action': None, 'reward': 2.581700193180704, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.58)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 2.75642999705
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 32, 't': 3, 'action': None, 'reward': 2.75642999704895, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.76)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 1.49312771561
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 31, 't': 4, 'action': None, 'reward': 1.4931277156053055, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.49)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: forward, reward: 1.39596182036
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 30, 't': 5, 'action': 'forward', 'reward': 1.3959618203646644, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.40)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: right, reward: 0.997711270646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 29, 't': 6, 'action': 'right', 'reward': 0.9977112706459244, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.00)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: left, reward: 1.356601279
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 28, 't': 7, 'action': 'left', 'reward': 1.3566012789966164, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.36)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: left, reward: -9.88357964804
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 27, 't': 8, 'action': 'left', 'reward': -9.883579648041817, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent attempted driving left through a red light. (rewarded -9.88)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: right, reward: 1.23729233143
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 26, 't': 9, 'action': 'right', 'reward': 1.2372923314258923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.24)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: left, reward: 2.28079870781
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 25, 't': 10, 'action': 'left', 'reward': 2.2807987078089256, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.28)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: right, reward: 1.52165760047
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 24, 't': 11, 'action': 'right', 'reward': 1.521657600472947, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 1.52)
66% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 194
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (3, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0545; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.97305109489
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.973051094887034, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.97)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.65102210438
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.6510221043767945, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.65)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.88821437725
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.888214377253216, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.89)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.00213096313
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0021309631259898, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.00)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.79352452722
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.7935245272152474, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.79)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.12726356261
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.127263562612198, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.13)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: forward, reward: 1.5810298466
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.5810298465995867, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.58)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 1.63917477915
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.6391747791534894, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.64)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 1.23280449685
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.2328044968494736, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.23)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: forward, reward: 0.932651159089
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 0.9326511590886621, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.93)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.31105568939
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.311055689393903, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.31)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.51913445459
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.5191344545856822, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.52)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.92406225936
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.9240622593572434, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.92)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: forward, reward: 2.15343807781
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 2.153438077810314, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.15)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: right, reward: -0.111500491502
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 6, 't': 14, 'action': 'right', 'reward': -0.1115004915016754, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded -0.11)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: right, reward: 1.12465236753
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 1.1246523675314792, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.12)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 5), heading: (0, -1), action: right, reward: 2.18912748155
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 2.189127481545686, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.19)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: right, reward: 0.624985986556
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 0.6249859865556293, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.62)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: -10.0341704853
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 18, 'action': 'left', 'reward': -10.034170485266367, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.03)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: 0.847641119143
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 1, 't': 19, 'action': None, 'reward': 0.8476411191433233, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.85)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 195
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (2, 6), deadline = 30
Simulating trial. . . 
epsilon = 0.0537; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0537; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: forward, reward: 0.176610403076
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': 0.17661040307554665, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.18)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: left, reward: 2.36726847512
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 29, 't': 1, 'action': 'left', 'reward': 2.367268475123484, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.37)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: forward, reward: 1.45169543228
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 28, 't': 2, 'action': 'forward', 'reward': 1.4516954322800717, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.45)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.19879975044
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.1987997504439234, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.20)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.80256365251
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.8025636525143138, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.80)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 2.43331971887
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 25, 't': 5, 'action': None, 'reward': 2.433319718866083, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.43)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: 1.01934296492
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 1.019342964924986, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.02)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 1.88538283905
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 1.885382839049112, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.89)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: forward, reward: 2.65292360034
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 22, 't': 8, 'action': 'forward', 'reward': 2.652923600335031, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.65)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 196
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (8, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0529; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: 0.306942508728
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 0.3069425087280042, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.31)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 1.63844482284
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'right'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.638444822836321, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'right')
Agent followed the waypoint right. (rewarded 1.64)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: forward, reward: 0.563946603121
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'right'), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': 0.5639466031210263, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'right')
Agent drove forward instead of right. (rewarded 0.56)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: right, reward: 2.64531208487
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 2.6453120848677605, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.65)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: forward, reward: 1.36480353385
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'right'), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.364803533845995, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'right')
Agent followed the waypoint forward. (rewarded 1.36)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: forward, reward: 1.38788872826
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 1.3878887282572443, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.39)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 1.59854298988
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 1.598542989879526, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.60)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 1.97301099128
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 1.973010991281048, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.97)
68% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 197
\-------------------------

Environment.reset(): Trial set up with start = (5, 5), destination = (8, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.0521; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: forward, reward: 1.55685037802
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'right'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 1.55685037801849, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'right')
Agent drove forward instead of right. (rewarded 1.56)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 4), heading: (1, 0), action: right, reward: 2.74985869528
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 2.749858695277458, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.75)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: right, reward: 0.617235672448
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 0.6172356724475667, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.62)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 2.77114727499
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.77114727499389, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.77)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 1.43990722376
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.439907223761257, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.44)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 2.02235062379
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.0223506237857514, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.02)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: left, reward: 2.66878858238
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 2.6687885823825086, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.67)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: forward, reward: 1.12807594843
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.1280759484257337, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.13)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.8017939649
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.8017939649001307, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.80)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.95429326021
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.9542932602074132, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.95)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.09408921883
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 2.094089218830784, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.09)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: left, reward: 0.931597048035
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 0.9315970480354518, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.93)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: right, reward: 0.110752138844
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 0.11075213884367097, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent drove right instead of forward. (rewarded 0.11)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: left, reward: 1.64275937917
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 12, 't': 13, 'action': 'left', 'reward': 1.6427593791665367, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.64)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: left, reward: 1.05062159892
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 11, 't': 14, 'action': 'left', 'reward': 1.0506215989175334, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.05)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 198
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (2, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0513; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 2.16971162155
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 2.1697116215510572, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.17)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: right, reward: 2.24146772711
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 2.2414677271133305, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 2.24)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 1.97286557494
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.9728655749438997, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 1.97)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: forward, reward: 1.54417090893
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 1.5441709089286861, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.54)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: left, reward: 1.09652141776
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.0965214177605105, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.10)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: right, reward: 2.90988940649
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 2.909889406489182, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.91)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 3), heading: (0, -1), action: None, reward: 1.88161989242
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.8816198924233778, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.88)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: forward, reward: 1.24171005686
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.2417100568607176, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.24)
68% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 199
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (7, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0505; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0505; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0505; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: right, reward: 0.419535575369
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 0.4195355753687666, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.42)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: forward, reward: 1.70223314576
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.7022331457570576, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.70)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: right, reward: 0.604313762933
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.604313762932771, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.60)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: None, reward: 1.66102814385
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.661028143854091, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.66)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: None, reward: 2.61368470845
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.613684708451771, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.61)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: left, reward: 2.41796911811
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.4179691181135494, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.42)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 2.32535331815
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.3253533181548085, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.33)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 1.69526443707
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.6952644370651475, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.70)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 0.111988179564
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.11198817956383611, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.11)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: None, reward: 1.38571827646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.3857182764611553, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.39)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: 2.49312939726
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.4931293972618302, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.49)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 2.14337012131
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.1433701213094722, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.14)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 1.19248754767
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.192487547674052, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.19)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: left, reward: 1.25433489345
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 1.254334893450032, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.25)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 200
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (6, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0498; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: None, reward: 0.883933988783
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 0.8839339887826898, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.88)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: right, reward: 2.11433122739
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 2.1143312273867156, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.11)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: left, reward: 1.90198047684
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': 'left', 'reward': 1.9019804768441784, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.90)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: right, reward: 2.35254959996
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 2.3525495999648864, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.35)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: right, reward: 1.5988916412
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 1.598891641199298, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.60)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 2.41764152886
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.4176415288593813, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.42)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 0.975030256762
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 0.9750302567615108, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.98)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 2.83953755821
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.8395375582076325, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.84)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.90641395229
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.906413952287195, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.91)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.02711436398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.027114363983583, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.03)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 3), heading: (0, 1), action: left, reward: 0.723522904563
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 15, 't': 10, 'action': 'left', 'reward': 0.723522904562976, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent drove left instead of forward. (rewarded 0.72)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: right, reward: 1.66697113108
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.6669711310769544, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.67)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 2.12679701609
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 2.126797016094989, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.13)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 201
\-------------------------

Environment.reset(): Trial set up with start = (4, 6), destination = (2, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0490; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0490; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: forward, reward: 2.51749627761
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 2.5174962776091023, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.52)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: 1.8557656847
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.8557656846995385, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.86)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 2.54835014716
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.5483501471625685, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.55)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: 1.243846767
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.243846766997687, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.24)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: None, reward: 1.61617282586
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.616172825861183, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.62)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: 2.47398040874
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.4739804087366517, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.47)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 202
\-------------------------

Environment.reset(): Trial set up with start = (2, 5), destination = (5, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0483; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0483; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.10305732584
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.1030573258447185, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.10)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.60070295326
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.6007029532638581, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.60)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.24749164753
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.24749164752785, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.25)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 2.7409427364
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.7409427363965793, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 2.13993133487
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.1399313348689164, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: forward, reward: 1.07008683837
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.0700868383746782, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.07)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: forward, reward: 0.932502763842
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.9325027638421288, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 0.93)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: forward, reward: 2.67497324509
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.6749732450928745, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.67)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 4), heading: (0, -1), action: left, reward: 2.41318203598
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 2.4131820359763934, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.41)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 203
\-------------------------

Environment.reset(): Trial set up with start = (6, 3), destination = (5, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0476; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: 2.0570140792
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.0570140791989755, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.06)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: right, reward: 1.5106362546
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.5106362545993088, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.51)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: None, reward: -5.18506262188
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': -5.185062621876163, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -5.19)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: right, reward: 1.52879948113
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.5287994811261263, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.53)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: None, reward: 2.70764923882
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.707649238818884, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.71)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: None, reward: 1.62021523715
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.620215237152266, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 1.62)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: None, reward: 2.60657430588
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.6065743058825612, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.61)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: left, reward: 1.83419721294
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.8341972129446011, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.83)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 0.464527640135
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.4645276401346977, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.46)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.05468607352
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.054686073516473, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.05)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.43428046175
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.4342804617495286, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.43)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: left, reward: 0.803929433377
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 0.8039294333768707, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 0.80)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: None, reward: 1.69728261874
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.697282618741774, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.70)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: forward, reward: 0.411757680192
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 0.4117576801920818, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.41)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 1.66599046124
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.6659904612413856, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.67)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 0.762358303815
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 0.7623583038149293, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.76)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 5), heading: (-1, 0), action: left, reward: 2.20169964608
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 2.2016996460845197, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.20)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: forward, reward: 1.14161114691
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 1.1416111469119696, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.14)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (5, 5), heading: (-1, 0), action: None, reward: 0.834513393419
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.8345133934189279, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.83)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: left, reward: 0.739867163099
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': 0.7398671630988249, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.74)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 204
\-------------------------

Environment.reset(): Trial set up with start = (2, 3), destination = (8, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0469; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: left, reward: 2.34581285175
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.345812851749714, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.35)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: left, reward: 1.22102625976
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.2210262597594426, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.22)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 2.88867176581
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.8886717658121284, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.89)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 2.1285625678
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.1285625678041105, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.13)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 1.44268606079
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.4426860607919978, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.44)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 2.71904765807
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.7190476580722707, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.72)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: left, reward: 0.3118718471
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 0.31187184709974636, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.31)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: forward, reward: 1.48064045167
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.4806404516730796, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 1.48)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: right, reward: 2.68405900327
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.684059003274185, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.68)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: right, reward: 2.48913302982
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 2.489133029817171, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.49)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: right, reward: 2.75213315631
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 2.7521331563059928, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.75)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: left, reward: 1.73017756805
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 1.7301775680493168, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.73)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: 0.459110538804
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 0.4591105388037511, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.46)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: forward, reward: 0.422973815794
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 0.42297381579353444, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.42)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: None, reward: 1.13403995333
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.1340399533293821, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.13)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: left, reward: 1.70239777605
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.7023977760528293, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.70)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: left, reward: 1.63483216933
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 1.634832169327418, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.63)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 1.98216387009
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 1.9821638700918713, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.98)
10% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 205
\-------------------------

Environment.reset(): Trial set up with start = (3, 6), destination = (2, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0462; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0462; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: 2.12992211759
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 2.129922117589542, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.13)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 1.42971608817
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.4297160881673818, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent drove forward instead of left. (rewarded 1.43)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.15490656983
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.1549065698272805, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.15)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.39921891109
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.3992189110880757, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.40)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.5048306793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.504830679299295, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.50)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: forward, reward: 1.87045979536
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.8704597953633761, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.87)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.53240646017
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 14, 't': 6, 'action': None, 'reward': 2.5324064601749905, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.53)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: 0.00937063268176
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 0.009370632681757751, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.01)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: right, reward: 1.65402012702
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.654020127021055, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.65)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: forward, reward: 1.32476899429
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.3247689942898984, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 1.32)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: 1.74773673147
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.7477367314656596, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.75)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: right, reward: 1.61756979216
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.6175697921601573, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.62)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: left, reward: 2.16097904722
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 12, 'action': 'left', 'reward': 2.160979047218146, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.16)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 1.85361832319
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.8536183231948122, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.85)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 1.00712804174
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.0071280417398147, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.01)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 2.24489256324
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.244892563243453, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 2.24)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 1.2184557801
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 4, 't': 16, 'action': None, 'reward': 1.2184557801036178, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.22)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: forward, reward: 1.53363569222
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 1.5336356922195216, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.53)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 2.17310340781
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 2, 't': 18, 'action': None, 'reward': 2.1731034078085116, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.17)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.76257931073
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.7625793107285306, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.76)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 206
\-------------------------

Environment.reset(): Trial set up with start = (1, 5), destination = (4, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0455; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: 2.74338782596
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.743387825964268, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.74)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: left, reward: 2.47124217546
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 2.471242175456161, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.47)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 2.12684933322
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.1268493332165863, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.13)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 1.47764942786
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 1.4776494278599261, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.48)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 2.54440111031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.544401110313299, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.54)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 1.21571010007
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.2157101000690815, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.22)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: None, reward: 0.952927042224
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 14, 't': 6, 'action': None, 'reward': 0.9529270422238039, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.95)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: left, reward: 0.425171390811
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 0.4251713908106016, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 0.43)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 2.83105238631
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.8310523863052537, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.83)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 0.96044917789
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 0.9604491778895017, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.96)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 207
\-------------------------

Environment.reset(): Trial set up with start = (1, 3), destination = (6, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0448; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: None, reward: 0.520136821804
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 0.5201368218035438, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 0.52)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 1.43380590335
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.4338059033532777, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.43)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: forward, reward: 2.61989614223
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': 2.619896142231254, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 2.62)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 2.18942101972
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 2.18942101971577, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.19)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: left, reward: 1.86755053813
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.8675505381310251, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.87)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: forward, reward: 2.92962034644
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.9296203464364003, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.93)
76% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 208
\-------------------------

Environment.reset(): Trial set up with start = (6, 5), destination = (7, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0442; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: forward, reward: 1.85842439969
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.858424399692075, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent followed the waypoint forward. (rewarded 1.86)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 0.996433984169
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 19, 't': 1, 'action': None, 'reward': 0.9964339841693884, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.00)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: None, reward: 1.28471791159
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.284717911589023, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.28)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: right, reward: 1.00466978354
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.004669783539912, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.00)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: forward, reward: 2.30295010533
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.302950105327735, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent followed the waypoint forward. (rewarded 2.30)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: right, reward: 1.81025231284
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 1.8102523128440464, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.81)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: left, reward: 2.83879765482
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 2.838797654821861, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.84)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 2), heading: (1, 0), action: left, reward: 1.04604480358
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.0460448035795724, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.05)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 209
\-------------------------

Environment.reset(): Trial set up with start = (1, 4), destination = (4, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0435; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 2.70549995759
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 2.705499957585412, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.71)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.663122406672
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 0.663122406671786, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.66)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 2.52683224585
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': 'left', 'reward': 2.5268322458486905, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.53)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: right, reward: 1.6744009682
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 1.6744009681976797, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.67)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: forward, reward: 1.64629014628
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.646290146280739, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.65)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: None, reward: 1.34212627231
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.3421262723120015, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.34)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (0, 1), action: None, reward: 2.13537801288
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 2.135378012883808, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: left, reward: 2.72415987928
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 2.7241598792834023, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.72)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: left, reward: -0.0259825361321
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 17, 't': 8, 'action': 'left', 'reward': -0.025982536132103218, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded -0.03)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: right, reward: 2.3812987104
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 2.3812987104042724, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.38)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: right, reward: 1.35157733521
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.3515773352063951, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 1.35)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: right, reward: 2.45728009042
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 2.4572800904178753, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.46)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: forward, reward: 0.684149695943
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 0.6841496959431752, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.68)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: None, reward: 1.02074585262
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.020745852618907, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.02)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: None, reward: 0.734332285856
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 0.7343322858560444, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.73)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: None, reward: 1.90722974222
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 15, 'action': None, 'reward': 1.9072297422213655, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.91)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: left, reward: 0.973691269319
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'left', 'reward': 0.973691269319479, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.97)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: left, reward: 2.24193970063
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 17, 'action': 'left', 'reward': 2.241939700626033, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.24)
28% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 210
\-------------------------

Environment.reset(): Trial set up with start = (3, 5), destination = (6, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0429; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0429; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.14182618567
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.1418261856657175, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.54457672216
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.544576722156518, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.54)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.71497378956
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.714973789559941, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.71)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.54128372082
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.5412837208151837, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.54)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.04070460538
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.040704605380481, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.04)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: left, reward: 1.18631062575
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.18631062574769, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 1.19)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: right, reward: 1.63486623446
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.634866234464767, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.63)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.46927871438
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.4692787143802584, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.47)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.39272390366
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.392723903661152, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.39)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 0.861685587616
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 0.8616855876161478, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.86)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 0.950260204964
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 0.9502602049637756, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.95)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.34391678891
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.3439167889091523, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.34)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.40796158817
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.40796158816655, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.41)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: forward, reward: 2.46688462855
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 2.466884628547877, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.47)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 1.4395483061
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 6, 't': 14, 'action': 'right', 'reward': 1.4395483061036147, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.44)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: 2.35965961137
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.3596596113704145, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.36)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: left, reward: 0.467334578992
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 0.46733457899236774, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.47)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: right, reward: -0.554100545325
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': -0.5541005453246391, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded -0.55)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: right, reward: 0.772898550613
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 2, 't': 18, 'action': 'right', 'reward': 0.7728985506130088, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.77)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: right, reward: 0.702636991301
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'right', 'reward': 0.7026369913009511, 'waypoint': 'right'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.70)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 211
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (1, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0422; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0422; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0422; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0422; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0422; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.37606437164
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.376064371644347, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.38)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.36110196119
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.3611019611939863, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.36)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 2.74368254296
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.74368254295944, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: -10.2329699147
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': -10.232969914688288, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.23)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.99145393716
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.9914539371559539, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.99)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: 1.94867466734
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.948674667338931, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.95)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: forward, reward: 2.19767796905
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.197677969046211, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.20)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: None, reward: 0.696347716985
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': None, 'reward': 0.696347716984594, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.70)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: right, reward: 1.38340158654
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.383401586537684, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.38)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: left, reward: 0.347488909597
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 0.3474889095966742, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.35)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 0.359888258286
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 10, 't': 10, 'action': None, 'reward': 0.35988825828573157, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.36)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 2.52652110512
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 2.526521105122055, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.53)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: right, reward: 1.22788614038
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.227886140376175, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.23)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.63301980855
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.633019808550415, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.63)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.32006307543
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.3200630754296807, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.32)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: left, reward: 1.86669776417
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.866697764170155, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.87)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 212
\-------------------------

Environment.reset(): Trial set up with start = (2, 4), destination = (5, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0416; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0416; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.69828207963
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.6982820796344908, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.70)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.06128000571
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.0612800057121767, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.06)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.32359121196
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.3235912119574866, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.32)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.89340029899
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.89340029898738, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.89)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.83184341169
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.8318434116882882, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.83)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 2.57644630088
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.5764463008768006, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.58)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.89853045494
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 0.898530454939903, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.90)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 0.943852904465
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 18, 't': 7, 'action': 'left', 'reward': 0.9438529044654742, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 0.94)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: None, reward: 1.32040051386
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.3204005138640094, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.32)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: forward, reward: 1.34388988504
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 1.3438898850435175, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.34)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: forward, reward: 2.02783547478
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 2.0278354747798084, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.03)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: right, reward: 1.30964318035
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.309643180345084, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 1.31)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 1.52495754914
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.5249575491424796, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.52)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 0.664118822862
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 0.6641188228619046, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.66)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: None, reward: 0.738392878055
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 0.7383928780547122, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.74)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: left, reward: 1.09944782013
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 10, 't': 15, 'action': 'left', 'reward': 1.0994478201313862, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.10)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: None, reward: 1.0892729504
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 16, 'action': None, 'reward': 1.0892729504033611, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.09)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: left, reward: 1.29997859173
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 17, 'action': 'left', 'reward': 1.2999785917309779, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.30)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: right, reward: 0.944881643101
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 7, 't': 18, 'action': 'right', 'reward': 0.9448816431007925, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.94)
24% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 213
\-------------------------

Environment.reset(): Trial set up with start = (1, 4), destination = (7, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0410; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0410; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0410; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0410; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.41868499855
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.4186849985477008, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.42)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.61091511065
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.610915110645017, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.61)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.79604619384
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.7960461938366965, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.80)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.43825025607
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.438250256065803, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.44)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: left, reward: -10.3533436376
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': -10.353343637625649, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -10.35)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 2.2879562922
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.287956292200816, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.29)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.34779895525
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.3477989552481942, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.35)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 2.21352508759
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.2135250875886046, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 2.28954183469
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.2895418346895853, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.29)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 2.25955570235
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.2595557023462094, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.26)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 2.37543097022
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.375430970219278, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.38)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: -0.169863375602
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': -0.16986337560229137, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded -0.17)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: left, reward: 1.937453811
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 12, 'action': 'left', 'reward': 1.9374538109970196, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.94)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 0.682256046407
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.682256046406581, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 0.68)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 214
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (8, 2), deadline = 35
Simulating trial. . . 
epsilon = 0.0404; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 2.26590543919
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 35, 't': 0, 'action': 'right', 'reward': 2.2659054391932805, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.27)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 1.00149246461
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'forward'), 'deadline': 34, 't': 1, 'action': None, 'reward': 1.0014924646107624, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.00)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: None, reward: 1.42198960221
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 33, 't': 2, 'action': None, 'reward': 1.4219896022117307, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.42)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: right, reward: 1.89490419537
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 32, 't': 3, 'action': 'right', 'reward': 1.8949041953678798, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.89)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 2.34233701025
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 31, 't': 4, 'action': None, 'reward': 2.3423370102460574, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.34)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 2.21098506518
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 30, 't': 5, 'action': None, 'reward': 2.2109850651802287, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.21)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.47438455771
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 29, 't': 6, 'action': None, 'reward': 1.474384557709012, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.47)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: right, reward: 1.1321973893
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 28, 't': 7, 'action': 'right', 'reward': 1.1321973892952197, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 1.13)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: right, reward: 1.60246163954
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 27, 't': 8, 'action': 'right', 'reward': 1.6024616395443663, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.60)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: 1.89904359359
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 26, 't': 9, 'action': None, 'reward': 1.8990435935900807, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.90)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 1.07684421188
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 25, 't': 10, 'action': 'right', 'reward': 1.0768442118805917, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.08)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: right, reward: 2.86192031577
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 24, 't': 11, 'action': 'right', 'reward': 2.86192031576741, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 2.86)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.19496569163
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 12, 'action': None, 'reward': 1.194965691634272, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.19)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: 2.14906653736
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 22, 't': 13, 'action': 'forward', 'reward': 2.1490665373576263, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.15)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 2.03524529011
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 21, 't': 14, 'action': None, 'reward': 2.0352452901081106, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.04)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: -4.35315428815
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 15, 'action': None, 'reward': -4.35315428815424, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent idled at a green light with no oncoming traffic. (rewarded -4.35)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: 0.731511132518
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 19, 't': 16, 'action': 'left', 'reward': 0.7315111325181515, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.73)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: 0.384544657626
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 18, 't': 17, 'action': 'forward', 'reward': 0.38454465762571133, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 0.38)
49% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: right, reward: 1.92106475772
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 17, 't': 18, 'action': 'right', 'reward': 1.9210647577156212, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.92)
46% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 1.23308950294
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 19, 'action': None, 'reward': 1.2330895029415, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.23)
43% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: left, reward: -9.36302146916
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 2, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 20, 'action': 'left', 'reward': -9.363021469163318, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent attempted driving left through a red light. (rewarded -9.36)
40% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 1.23885848196
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 21, 'action': 'forward', 'reward': 1.238858481955489, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.24)
37% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 215
\-------------------------

Environment.reset(): Trial set up with start = (6, 2), destination = (5, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0398; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: right, reward: 0.130847861302
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 0.1308478613015287, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.13)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: 2.68631344994
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.6863134499424133, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.69)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: left, reward: 1.06760978486
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.067609784857927, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.07)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 5), heading: (0, 1), action: forward, reward: 1.61788146746
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 1.617881467460702, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent followed the waypoint forward. (rewarded 1.62)
80% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 216
\-------------------------

Environment.reset(): Trial set up with start = (1, 2), destination = (6, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0392; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0392; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0392; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0392; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0392; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: 2.78169076889
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.78169076888555, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.78)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 1.20222486243
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.202224862432894, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.20)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.49862058755
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.4986205875502059, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.50)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 1.2623104808
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.2623104808005032, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.26)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: 1.53440962462
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.5344096246150478, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.53)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 2.81800839418
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 2.818008394180568, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.82)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 217
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (7, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0386; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: None, reward: 1.02054314851
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.020543148506688, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.02)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: None, reward: 2.69972987448
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.6997298744760645, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.70)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: None, reward: 2.42652771211
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.426527712114008, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.43)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: None, reward: 2.89716278956
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.8971627895587435, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.90)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: forward, reward: 2.01248653264
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.012486532636938, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.01)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: None, reward: 1.841432686
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.841432686003996, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.84)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: forward, reward: 2.37340308163
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 2.3734030816265417, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.37)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.58780105988
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.5878010598818844, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.59)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 2.73890411498
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.738904114977, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.74)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 2.15085635882
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.1508563588179426, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.15)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 0.857737940259
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 0.8577379402586712, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.86)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 1.25443501031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.2544350103136754, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.25)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 2.42570242178
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 2.4257024217770717, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.43)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 0.949353673115
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.9493536731147869, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 0.95)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 2.47686935519
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 6, 't': 14, 'action': None, 'reward': 2.476869355188577, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.48)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.50392216008
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 15, 'action': None, 'reward': 1.503922160078434, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.50)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: forward, reward: 1.6736332517
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 1.6736332516979167, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.67)
15% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 218
\-------------------------

Environment.reset(): Trial set up with start = (3, 6), destination = (6, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0380; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.39516748855
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.395167488554977, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.40)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: right, reward: 1.37099617319
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.370996173191844, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.37)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: None, reward: 2.3209505368
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.3209505367962606, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 2.32)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: right, reward: 0.510008757937
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.510008757937321, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.51)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: None, reward: 1.21055724062
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.210557240621079, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.21)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: left, reward: 2.34116563327
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.3411656332711894, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.34)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: left, reward: -0.0318680421235
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': -0.03186804212350647, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded -0.03)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: right, reward: 2.12302417096
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 2.1230241709564903, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.12)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: right, reward: 1.99688738908
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.9968873890765202, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.00)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 219
\-------------------------

Environment.reset(): Trial set up with start = (8, 4), destination = (2, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0374; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.84218574272
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.8421857427220574, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.84)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 2.1434706628
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.1434706628046714, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 2.87707710626
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.8770771062647333, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.88)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.00013146947
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0001314694681216, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 2.73028582407
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.7302858240657653, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.73)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.30619145349
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.3061914534899044, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: forward, reward: 1.22866589145
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.2286658914522413, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.23)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.9526193891
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.9526193891009536, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.95)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.53208989772
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.5320898977209056, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.53)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 1.42198407615
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 1.4219840761523836, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.42)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 2.06341137735
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 2.0634113773475145, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 2.06)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: forward, reward: 1.91906296407
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 1.91906296406941, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.92)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 220
\-------------------------

Environment.reset(): Trial set up with start = (5, 2), destination = (3, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0369; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: left, reward: 1.74368294909
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 1.743682949093911, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.74)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: forward, reward: 1.7842962859
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.7842962858973526, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 1.78)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.87483895727
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.8748389572697586, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.87)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 2.86620121071
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.8662012107054986, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.87)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.30470198132
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.3047019813194365, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.30)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: None, reward: 1.37875377082
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.3787537708167705, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.38)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: left, reward: 2.72542637382
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 2.7254263738198707, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.73)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: forward, reward: 0.998493140239
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 0.998493140238943, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.00)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 221
\-------------------------

Environment.reset(): Trial set up with start = (2, 2), destination = (5, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0363; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: forward, reward: 1.44500357259
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.4450035725890575, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 1.45)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: 1.17031061473
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.1703106147329225, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.17)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: 2.73843475372
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.738434753723113, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.74)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 1.84906148885
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 1.8490614888541685, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.85)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.1150808191
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 2.115080819099128, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.12)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 2.37309254271
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.373092542712275, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.37)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: None, reward: 1.26379797553
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.2637979755268602, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.26)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: forward, reward: 1.57859897179
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.5785989717896018, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.58)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 0.545809287998
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 0.5458092879983772, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.55)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: right, reward: 1.1421627847
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.1421627846983406, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.14)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: right, reward: 0.363338607816
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 0.3633386078159767, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.36)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 2.32231494845
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 2.3223149484491623, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.32)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.05032289325
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.05032289324951, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.05)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 2), heading: (0, -1), action: right, reward: 1.14970045756
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 1.149700457560849, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.15)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: forward, reward: 0.780999374465
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'right'), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': 0.780999374464907, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'right')
Agent drove forward instead of left. (rewarded 0.78)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: right, reward: 1.45668362588
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 5, 't': 15, 'action': 'right', 'reward': 1.4566836258796856, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.46)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 0.609281975054
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 4, 't': 16, 'action': 'right', 'reward': 0.6092819750535212, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.61)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: 1.55063041124
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 3, 't': 17, 'action': 'right', 'reward': 1.5506304112426235, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.55)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 0.521608461969
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 2, 't': 18, 'action': 'forward', 'reward': 0.5216084619691066, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.52)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: 1.7628980286
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': 1.762898028600464, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.76)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 222
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (2, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0358; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: left, reward: 0.105204917853
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 0.10520491785286445, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.11)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: left, reward: 1.33098341041
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 1.330983410414584, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.33)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 1.92066021514
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.9206602151406502, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.92)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 2.6177876688
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.6177876687963675, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.62)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 1.17920447874
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.179204478735103, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.18)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: left, reward: 1.0872124568
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.0872124567991928, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.09)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: forward, reward: 0.942146071261
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.94214607126061, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.94)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 7), heading: (-1, 0), action: forward, reward: 1.68770937538
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.6877093753772472, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent followed the waypoint forward. (rewarded 1.69)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: left, reward: 1.14353292558
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 1.143532925582217, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.14)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: None, reward: 1.53007686524
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.5300768652438066, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.53)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: right, reward: 2.03239447489
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 2.0323944748914715, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.03)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: right, reward: 1.57652579388
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 1.5765257938828865, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 1.58)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: right, reward: 1.83327231365
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.8332723136492557, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.83)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: None, reward: 0.743163804197
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 7, 't': 13, 'action': None, 'reward': 0.743163804197428, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.74)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: None, reward: 1.49642059861
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.4964205986072612, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.50)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 6), heading: (0, -1), action: left, reward: 1.65343632237
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.6534363223748278, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.65)
20% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 223
\-------------------------

Environment.reset(): Trial set up with start = (3, 5), destination = (1, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0353; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0353; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0353; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: forward, reward: 1.70623987215
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'right'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.706239872148981, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'right')
Agent drove forward instead of left. (rewarded 1.71)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: None, reward: 1.01521006195
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.015210061950089, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.02)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: None, reward: 1.80210446665
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.8021044666533585, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.80)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: None, reward: 2.23842913993
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.2384291399269953, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.24)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 4), heading: (1, 0), action: right, reward: 1.76604107634
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.7660410763351946, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.77)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 5), heading: (0, 1), action: right, reward: 0.850268792525
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'forward'), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 0.8502687925245083, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'forward')
Agent drove right instead of left. (rewarded 0.85)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: right, reward: 0.975546682782
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.9755466827818497, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.98)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: forward, reward: 1.12161381918
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.1216138191760325, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.12)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 2.67096576989
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 2.67096576988589, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.67)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: right, reward: 2.56318141457
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 2.563181414573747, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.56)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 2.09436780561
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.0943678056056374, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.09)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 1.33250092635
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 9, 't': 11, 'action': None, 'reward': 1.3325009263517376, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.33)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 1.45182638388
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.451826383876194, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.45)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: forward, reward: 1.09383652117
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.0938365211677135, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.09)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 224
\-------------------------

Environment.reset(): Trial set up with start = (4, 7), destination = (8, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0347; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: None, reward: 1.67177246158
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.6717724615785243, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.67)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: None, reward: 2.82872851744
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.8287285174382135, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 2.83)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: right, reward: 1.52745226184
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.527452261840878, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.53)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: None, reward: 1.01798415754
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.0179841575411028, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.02)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: None, reward: 1.99715829327
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.9971582932740575, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.00)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: left, reward: 1.08695720296
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 1.0869572029570327, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.09)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 6), heading: (-1, 0), action: None, reward: 1.90693764298
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.9069376429817226, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.91)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: forward, reward: 1.09152715686
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.0915271568584266, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.09)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 2.12980787657
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.1298078765660966, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.13)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: left, reward: 0.372559027652
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 0.37255902765181137, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.37)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: right, reward: 1.73994996276
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.73994996276022, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.74)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.23555869059
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 11, 'action': None, 'reward': 1.2355586905938951, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.24)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 1.75469975568
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 1.7546997556795003, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.75)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: left, reward: 2.27362557877
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'left', 'reward': 2.2736255787661315, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.27)
44% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 225
\-------------------------

Environment.reset(): Trial set up with start = (1, 4), destination = (4, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0342; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.09418119644
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.0941811964377977, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.09)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 2.24456392816
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.244563928162518, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.24)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.97906396974
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.9790639697436683, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.98)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.44954160411
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.4495416041110185, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.45)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 2.67182550909
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.671825509087157, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.67)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: 0.995282259689
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 0.9952822596891735, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.00)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.3848385743
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.3848385742977394, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.38)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 2.47538271177
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.4753827117735616, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.48)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 2.42470743329
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.424707433290119, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.42)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 2.52328579352
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 2.5232857935204427, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.52)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 2.02315244513
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 2.0231524451295466, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.02)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 1.32103818389
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 1.3210381838925715, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.32)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 1.95122860772
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 1.9512286077212244, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.95)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: forward, reward: 2.04492733292
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 2.0449273329179194, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.04)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 1.3479634055
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 1.347963405500502, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.35)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 226
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (7, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0337; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 2.74285505205
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 2.7428550520509676, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.74)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 0.931171931105
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 24, 't': 1, 'action': None, 'reward': 0.9311719311053717, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.93)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 1.03578050958
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.035780509578161, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.04)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 2.0148208212
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 2.014820821201787, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.01)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: right, reward: 0.687904336669
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 0.6879043366687526, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.69)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 1.40704104791
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.40704104791109, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.41)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 1.31960008718
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.3196000871755287, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.32)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 2.40913763423
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.4091376342259605, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.41)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: None, reward: 2.44772789386
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.4477278938572615, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.45)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: left, reward: 1.1492582659
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 1.1492582658955923, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.15)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.90904315446
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.9090431544553095, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.91)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: forward, reward: 1.98583090919
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.9858309091926467, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.99)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 2.73771552645
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 12, 'action': None, 'reward': 2.7377155264538002, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: forward, reward: -0.135153061295
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': -0.13515306129537374, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded -0.14)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 0.921883264049
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 11, 't': 14, 'action': None, 'reward': 0.9218832640493098, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.92)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: None, reward: 1.77587127673
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 10, 't': 15, 'action': None, 'reward': 1.7758712767275697, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.78)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: left, reward: 1.56431969431
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 9, 't': 16, 'action': 'left', 'reward': 1.5643196943131323, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.56)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 0.760838994666
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 8, 't': 17, 'action': None, 'reward': 0.7608389946660159, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.76)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 0.866357971577
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 0.8663579715773015, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.87)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 2.04256736078
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 19, 'action': None, 'reward': 2.042567360781531, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.04)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: None, reward: 0.953068729784
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 20, 'action': None, 'reward': 0.9530687297841953, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.95)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: forward, reward: -0.248051304308
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': -0.24805130430793743, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded -0.25)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: None, reward: 1.5083278013
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 3, 't': 22, 'action': None, 'reward': 1.508327801296861, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.51)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: None, reward: 0.957061996581
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 2, 't': 23, 'action': None, 'reward': 0.9570619965805816, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.96)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (6, 6), heading: (0, 1), action: None, reward: 0.888850522252
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 1, 't': 24, 'action': None, 'reward': 0.888850522251609, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.89)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 227
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (3, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0332; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: left, reward: 2.64615342696
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.6461534269606055, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.65)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: left, reward: 0.298027050385
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 19, 't': 1, 'action': 'left', 'reward': 0.29802705038495214, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.30)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: None, reward: 1.5759819124
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.5759819123982404, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.58)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: forward, reward: 2.65048316977
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.650483169766542, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.65)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: right, reward: 1.80020047968
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.800200479681172, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.80)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: left, reward: 1.45546698766
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.4554669876610362, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.46)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 1.60681232071
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.6068123207147798, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.61)
65% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 228
\-------------------------

Environment.reset(): Trial set up with start = (3, 5), destination = (6, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0327; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.22686684534
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.226866845342223, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.23)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.38400730924
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.384007309235692, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.38)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.66004548908
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.6600454890832954, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.66)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.00694031599
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0069403159879882, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.01)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.77729090564
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.7772909056363646, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.78)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: left, reward: 2.36474516308
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.364745163079432, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.36)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: left, reward: 2.51334802682
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 2.5133480268158053, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.51)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: forward, reward: 1.23735135566
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.2373513556616529, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.24)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.29283400087
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.29283400086953, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.29)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.714534171
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.714534171000916, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.71)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: forward, reward: 1.99805609063
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 1.9980560906308042, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.00)
45% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 229
\-------------------------

Environment.reset(): Trial set up with start = (1, 2), destination = (6, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0322; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0322; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0322; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 2.5094771338
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.5094771338010293, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.51)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 2.98265932004
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.9826593200407903, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.98)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 2.69506424667
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.695064246670794, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.70)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 1.17796010559
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.1779601055875284, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.18)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 1.39103350429
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.391033504293991, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.39)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 2.06457864143
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.064578641425882, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.06)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 1.72287242273
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.7228724227341947, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.72)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: 0.987137508774
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.9871375087736678, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.99)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: None, reward: 1.83971773893
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.8397177389296522, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.84)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: None, reward: 2.09884602841
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.0988460284077264, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.10)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: None, reward: 2.17436585422
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 10, 't': 10, 'action': None, 'reward': 2.1743658542216227, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.17)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: left, reward: 2.45434832758
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 2.454348327582852, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.45)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 230
\-------------------------

Environment.reset(): Trial set up with start = (6, 6), destination = (1, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0317; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: right, reward: 1.18366062589
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 1.183660625887541, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.18)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: right, reward: 1.15543059022
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.1554305902237552, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.16)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 5), heading: (1, 0), action: right, reward: 2.24323428033
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 2.2432342803303795, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.24)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 5), heading: (1, 0), action: forward, reward: 1.89987239516
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 1.8998723951616356, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 1.90)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: right, reward: 1.56258426952
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.5625842695210066, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 1.56)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: left, reward: 1.40340952817
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.4034095281698964, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.40)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: None, reward: 1.30888787403
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.3088878740255632, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: left, reward: 0.863911547023
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 0.8639115470227869, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 0.86)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: right, reward: 2.79283405596
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.792834055957278, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.79)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 231
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (6, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0313; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0313; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 0.198645276572
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 0.19864527657156916, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 0.20)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: forward, reward: 2.24888542944
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': 2.2488854294435683, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.25)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: None, reward: 0.978862621681
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 0.978862621680991, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.98)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: forward, reward: 1.26735250197
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 1.26735250196591, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.27)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: right, reward: 1.79413792974
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 1.7941379297423405, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.79)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 1.73893888004
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.7389388800374426, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.74)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 2.32036112145
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 2.320361121452883, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.32)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 2.41349805621
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.4134980562105293, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.41)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 0.957224041133
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 17, 't': 8, 'action': None, 'reward': 0.9572240411331607, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.96)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: left, reward: 2.63269266177
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 9, 'action': 'left', 'reward': 2.6326926617719497, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.63)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: 1.67510171692
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.6751017169191225, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.68)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: forward, reward: 1.22632472541
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.2263247254088792, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 1.23)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: 1.57770285894
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': 1.5777028589428206, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.58)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 0.934668302445
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 0.9346683024447102, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.93)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: 2.08961031035
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 2.0896103103473314, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.09)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 0.703945578689
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 15, 'action': 'forward', 'reward': 0.7039455786893463, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.70)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: forward, reward: 2.23626902068
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 2.236269020678793, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.24)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 2.51301985614
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 8, 't': 17, 'action': 'right', 'reward': 2.5130198561366264, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.51)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 1.00406688259
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.0040668825910113, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: forward, reward: 1.33918611859
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 6, 't': 19, 'action': 'forward', 'reward': 1.3391861185910823, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.34)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 0.981535116193
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 5, 't': 20, 'action': 'right', 'reward': 0.981535116192803, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.98)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: left, reward: 0.853353861802
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 4, 't': 21, 'action': 'left', 'reward': 0.8533538618018279, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 0.85)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 2.04713916005
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 3, 't': 22, 'action': None, 'reward': 2.047139160046491, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.05)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 0.355028819457
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 2, 't': 23, 'action': None, 'reward': 0.35502881945738296, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.36)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 0.246817349775
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 1, 't': 24, 'action': None, 'reward': 0.24681734977523728, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.25)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 232
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (5, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0308; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 1.17410074775
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 1.1741007477520715, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.17)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: forward, reward: 1.29672506625
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': 1.2967250662470562, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.30)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 2), heading: (0, -1), action: right, reward: 1.27783807033
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.2778380703344219, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.28)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: forward, reward: 1.67618322816
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 1.6761832281634665, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.68)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: forward, reward: 1.7199987583
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.7199987582973326, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent followed the waypoint forward. (rewarded 1.72)
80% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 233
\-------------------------

Environment.reset(): Trial set up with start = (2, 3), destination = (1, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0303; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: left, reward: 2.29579264189
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.295792641891176, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.30)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: right, reward: 0.0836933206328
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.08369332063279622, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 0.08)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: right, reward: 0.336448899686
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.3364488996857683, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.34)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: None, reward: 0.743458543964
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 17, 't': 3, 'action': None, 'reward': 0.7434585439635591, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.74)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: right, reward: 2.71390594828
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 2.7139059482794563, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.71)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: forward, reward: 1.23685047846
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.2368504784607408, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.24)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 1.74044452475
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.74044452475017, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.74)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: forward, reward: 0.965415808898
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 0.9654158088978502, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 0.97)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: forward, reward: 2.82040016124
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 2.8204001612442644, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.82)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 234
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (1, 2), deadline = 30
Simulating trial. . . 
epsilon = 0.0299; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 1.86790015136
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.867900151364177, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 1.87)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: right, reward: 1.52652970827
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.5265297082667781, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 1.53)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: right, reward: 1.9012788278
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.9012788277954376, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.90)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: None, reward: 2.79747635126
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 27, 't': 3, 'action': None, 'reward': 2.7974763512601895, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.80)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: left, reward: 2.15223360402
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 26, 't': 4, 'action': 'left', 'reward': 2.1522336040229018, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.15)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: None, reward: 1.1165931788
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 25, 't': 5, 'action': None, 'reward': 1.1165931787952006, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.12)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: None, reward: 2.7838218239
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 24, 't': 6, 'action': None, 'reward': 2.7838218238981094, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.78)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: right, reward: 1.18311389998
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 1.1831138999828141, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.18)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: 1.31323152222
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.3132315222235345, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: 1.55020976849
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 21, 't': 9, 'action': None, 'reward': 1.550209768493252, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.55)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: left, reward: 0.914276647538
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'left', 'reward': 0.9142766475384818, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.91)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 1.50071004607
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 19, 't': 11, 'action': None, 'reward': 1.5007100460739948, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.50)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.09251563026
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'left'), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.0925156302575907, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 2.09)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.0440295209
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 13, 'action': None, 'reward': 2.044029520896732, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.04)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 1.566377923
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 14, 'action': None, 'reward': 1.566377922998963, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.57)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 1.6752351773
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.6752351773046923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.68)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: forward, reward: 2.62860967122
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 16, 'action': 'forward', 'reward': 2.6286096712151985, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.63)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 1.47100939213
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 17, 'action': None, 'reward': 1.4710093921341907, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.47)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: right, reward: 1.40312943708
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 1.4031294370802612, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.40)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 1.31358304615
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 19, 'action': None, 'reward': 1.3135830461481273, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 2), heading: (0, 1), action: None, reward: 1.78609727708
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 10, 't': 20, 'action': None, 'reward': 1.7860972770800714, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.79)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: left, reward: 1.91095137366
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'left', 'reward': 1.9109513736556845, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.91)
27% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 235
\-------------------------

Environment.reset(): Trial set up with start = (2, 3), destination = (7, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0295; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: left, reward: 2.73144307752
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.7314430775237777, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.73)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: forward, reward: 0.649670060237
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 0.6496700602368483, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 0.65)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: right, reward: 0.157033998772
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 0.1570339987717294, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.16)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: right, reward: 2.76047280536
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 2.760472805355075, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.76)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: right, reward: 2.11973317162
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 2.1197331716210464, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.12)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: 2.01937442527
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': 2.0193744252723818, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.02)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: None, reward: 1.81859508159
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.818595081592141, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.82)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: forward, reward: 1.67846808923
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.6784680892339578, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.68)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 2.27443688803
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 2.274436888029304, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.27)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 2.34224770213
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 2.3422477021310124, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.34)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 1.89595213003
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.895952130026498, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.90)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 2.65690537234
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.6569053723386817, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.66)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 1.83510079101
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.8351007910104493, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.84)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 1.91443927309
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 1.9144392730911028, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.91)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 236
\-------------------------

Environment.reset(): Trial set up with start = (6, 4), destination = (2, 2), deadline = 30
Simulating trial. . . 
epsilon = 0.0290; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0290; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 4), heading: (0, -1), action: None, reward: 1.49031750078
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.4903175007806926, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.49)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: right, reward: 1.18698986684
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 1.1869898668410663, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.19)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 4), heading: (1, 0), action: None, reward: 1.07165290973
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.071652909734146, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.07)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: left, reward: 0.934659631992
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'left'), 'deadline': 27, 't': 3, 'action': 'left', 'reward': 0.9346596319924622, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'left')
Agent drove left instead of forward. (rewarded 0.93)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: right, reward: 1.52233705007
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 1.5223370500668731, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.52)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: 1.36279461277
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 1.3627946127654498, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.36)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 0.674687475229
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 0.6746874752292228, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.67)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.89057511357
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 23, 't': 7, 'action': None, 'reward': 1.8905751135683098, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.89)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.8293914411
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.8293914410999321, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.83)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: left, reward: 2.43966425595
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'left', 'reward': 2.439664255950878, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.44)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.0511248973024
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 20, 't': 10, 'action': 'right', 'reward': 0.05112489730240721, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.05)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 2.70212667917
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 2.702126679165696, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.70)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 1.70249422468
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 12, 'action': None, 'reward': 1.7024942246806227, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.70)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: forward, reward: 1.77436083553
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 17, 't': 13, 'action': 'forward', 'reward': 1.7743608355271812, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.77)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 1.5918309963
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 1.591830996301996, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 1.59)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.80766554123
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 15, 'action': None, 'reward': 1.8076655412259415, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.81)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.75974947881
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.7597494788098411, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.76)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 0.539269614963
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 0.5392696149634386, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 0.54)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: forward, reward: 0.379843552037
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 12, 't': 18, 'action': 'forward', 'reward': 0.37984355203749276, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 0.38)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: right, reward: 1.53999119183
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 11, 't': 19, 'action': 'right', 'reward': 1.5399911918327795, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.54)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: -0.27016204743
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 10, 't': 20, 'action': 'right', 'reward': -0.2701620474297979, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded -0.27)
30% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: forward, reward: 1.69748493611
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 21, 'action': 'forward', 'reward': 1.6974849361105895, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.70)
27% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: None, reward: 2.50834857411
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 8, 't': 22, 'action': None, 'reward': 2.508348574110438, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.51)
23% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: forward, reward: 2.04889130277
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 23, 'action': 'forward', 'reward': 2.0488913027655817, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.05)
20% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: forward, reward: 0.884840215144
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 6, 't': 24, 'action': 'forward', 'reward': 0.884840215144278, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.88)
17% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 237
\-------------------------

Environment.reset(): Trial set up with start = (2, 5), destination = (1, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0286; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: right, reward: 2.69799037279
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'right'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.6979903727914367, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'right')
Agent followed the waypoint right. (rewarded 2.70)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: right, reward: 0.490512054906
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.4905120549061376, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 0.49)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: right, reward: 1.5351723383
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.5351723382990659, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.54)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.721387876351
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.7213878763510043, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.72)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: right, reward: 0.979591512272
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.9795915122724661, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 0.98)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 6), heading: (0, 1), action: left, reward: 2.33586063528
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.3358606352762328, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.34)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: forward, reward: 1.39643677006
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 1.3964367700633784, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.40)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: forward, reward: 2.460694797
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.460694796999271, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.46)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 238
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (7, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0282; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0282; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0282; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 0.934306220586
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 25, 't': 0, 'action': None, 'reward': 0.9343062205857537, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.93)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 1.04493680829
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.0449368082936548, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.04)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: right, reward: 2.31617328999
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 2.3161732899888294, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.32)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 1.41670467869
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 1.4167046786881072, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.42)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: left, reward: 2.74308878374
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 2.743088783740494, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.74)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.86130554351
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.861305543507986, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.86)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.86434249786
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 19, 't': 6, 'action': None, 'reward': 2.864342497859049, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.86)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: right, reward: 0.432200286455
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 0.43220028645545217, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.43)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: 2.34401640971
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.3440164097105765, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.34)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: 0.909386503072
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 9, 'action': None, 'reward': 0.9093865030719359, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.91)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 5), heading: (0, -1), action: None, reward: 2.25159107483
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 10, 'action': None, 'reward': 2.2515910748275596, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.25)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 5), heading: (-1, 0), action: left, reward: 2.02291198432
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 2.0229119843232457, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.02)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: left, reward: 1.82375060379
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 1.8237506037881004, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.82)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: None, reward: 1.77421939425
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.774219394247625, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.77)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 6), heading: (0, 1), action: None, reward: 2.66483358886
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 11, 't': 14, 'action': None, 'reward': 2.6648335888559114, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.66)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: right, reward: 1.41041084322
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 1.4104108432195681, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.41)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: left, reward: 1.84518620722
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 9, 't': 16, 'action': 'left', 'reward': 1.845186207216198, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.85)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: 2.36216221079
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 8, 't': 17, 'action': None, 'reward': 2.3621622107889273, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.36)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (0, 1), action: None, reward: 1.90473591179
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.9047359117924008, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.90)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: left, reward: 1.18688571851
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 6, 't': 19, 'action': 'left', 'reward': 1.186885718509032, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.19)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: right, reward: 0.909273241907
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 5, 't': 20, 'action': 'right', 'reward': 0.9092732419070273, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.91)
16% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 239
\-------------------------

Environment.reset(): Trial set up with start = (6, 3), destination = (4, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0277; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 1.6629779807
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.6629779806950655, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.66)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: 2.65412271683
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.654122716826363, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.65)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: forward, reward: 2.92655342129
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 2.926553421293411, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.93)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 1.56771620473
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.5677162047342201, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.57)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 2.74648156682
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 2.746481566817001, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.75)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 1.61546216618
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.6154621661804751, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.62)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 1.99201072805
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.992010728050876, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.99)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 1.78735656227
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 7, 'action': None, 'reward': 1.7873565622695897, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.79)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 2.24291444913
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.242914449127995, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.24)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: forward, reward: 2.03709545551
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.0370954555145104, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.04)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 240
\-------------------------

Environment.reset(): Trial set up with start = (1, 7), destination = (7, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0273; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: right, reward: 2.17045512329
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.1704551232909184, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 2.17)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 0.0441918051445
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.04419180514449306, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.04)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: 2.96154767689
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 2.9615476768948126, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.96)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 2.71506205171
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.7150620517091215, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.72)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: left, reward: 1.3622542042
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.3622542041972867, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.36)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: forward, reward: 2.78175600884
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 2.7817560088354796, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.78)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (-1, 0), action: right, reward: 0.203588336978
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.20358833697776313, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.20)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: 0.974696639256
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.9746966392562664, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent drove right instead of left. (rewarded 0.97)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: right, reward: 2.36373517718
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 2.3637351771827353, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.36)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: right, reward: 2.16725524457
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 2.167255244572506, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 2.17)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: left, reward: 0.0624729347695
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 0.06247293476951088, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.06)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: right, reward: 2.26117864755
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 2.2611786475486557, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.26)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: right, reward: 1.54769750051
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.5476975005052642, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.55)
35% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 241
\-------------------------

Environment.reset(): Trial set up with start = (3, 7), destination = (8, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0269; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 2.45255263411
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.452552634105495, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.45)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 1.96184142009
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.9618414200868466, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.96)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: right, reward: 1.58489615793
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.5848961579275396, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.58)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 1.35990237725
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.3599023772511643, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.36)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (1, 0), action: None, reward: 2.29636300362
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.296363003624417, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.30)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: left, reward: 1.94276770037
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 1.9427677003727342, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.94)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: None, reward: 1.71263846154
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.7126384615427828, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.71)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: right, reward: 0.170322290402
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 0.17032229040217284, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 0.17)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: forward, reward: 2.28508302736
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 2.285083027357891, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.29)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: forward, reward: 2.28664678379
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 2.2866467837853275, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.29)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 1.15614952763
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 1.1561495276259528, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.16)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: left, reward: 2.24232477229
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'left', 'reward': 2.2423247722857234, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.24)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: -0.0248355214431
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 13, 't': 12, 'action': 'forward', 'reward': -0.024835521443066444, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded -0.02)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 1.06764423729
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 1.067644237291775, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.07)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: right, reward: 1.85321121941
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 1.8532112194129584, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.85)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: left, reward: 1.39676582951
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 10, 't': 15, 'action': 'left', 'reward': 1.396765829512956, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.40)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: forward, reward: 1.44867122295
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 1.4486712229470453, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.45)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 0.748130532352
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 8, 't': 17, 'action': None, 'reward': 0.748130532351647, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.75)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.1420468554
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.142046855397347, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.14)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 1.37725885742
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 6, 't': 19, 'action': None, 'reward': 1.377258857418376, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.38)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: None, reward: 2.18492929092
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 20, 'action': None, 'reward': 2.1849292909220885, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.18)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 5), heading: (0, 1), action: forward, reward: 2.24240097276
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': 2.2424009727610708, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.24)
12% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 242
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (1, 4), deadline = 35
Simulating trial. . . 
epsilon = 0.0265; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: forward, reward: 0.884057824943
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 35, 't': 0, 'action': 'forward', 'reward': 0.8840578249427562, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 0.88)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: right, reward: 0.466181372994
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 34, 't': 1, 'action': 'right', 'reward': 0.4661813729935953, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.47)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: right, reward: 1.74794318052
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 33, 't': 2, 'action': 'right', 'reward': 1.7479431805243664, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded 1.75)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 6), heading: (1, 0), action: None, reward: 1.18554471835
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 32, 't': 3, 'action': None, 'reward': 1.1855447183482535, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.19)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (6, 6), heading: (1, 0), action: forward, reward: 1.30173845138
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 31, 't': 4, 'action': 'forward', 'reward': 1.3017384513768784, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.30)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: forward, reward: 1.79743615584
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 30, 't': 5, 'action': 'forward', 'reward': 1.7974361558388354, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.80)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 0.431268440157
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 29, 't': 6, 'action': 'right', 'reward': 0.43126844015700705, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.43)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 2.75459893914
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 28, 't': 7, 'action': None, 'reward': 2.754598939136582, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.75)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 1.8092905048
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 27, 't': 8, 'action': None, 'reward': 1.8092905047994512, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.81)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 2.18051966397
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 26, 't': 9, 'action': None, 'reward': 2.1805196639725963, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.18)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 1.13958670564
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 10, 'action': None, 'reward': 1.1395867056448472, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.14)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: left, reward: 1.36314795837
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 24, 't': 11, 'action': 'left', 'reward': 1.3631479583666655, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.36)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: None, reward: 1.77510355647
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 12, 'action': None, 'reward': 1.775103556465889, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.78)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: forward, reward: 2.73439922298
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 22, 't': 13, 'action': 'forward', 'reward': 2.734399222975607, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.73)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: -0.00687044330098
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'forward'), 'deadline': 21, 't': 14, 'action': None, 'reward': -0.006870443300980855, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded -0.01)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 2), heading: (0, 1), action: right, reward: 1.99874668645
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 15, 'action': 'right', 'reward': 1.998746686447423, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.00)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 3), heading: (0, 1), action: forward, reward: 2.15349371387
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 16, 'action': 'forward', 'reward': 2.1534937138677988, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.15)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: right, reward: 0.38493367349
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 18, 't': 17, 'action': 'right', 'reward': 0.38493367349010066, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.38)
49% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.75779779728
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 17, 't': 18, 'action': None, 'reward': 1.757797797278662, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.76)
46% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 1.4255486864
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 16, 't': 19, 'action': None, 'reward': 1.4255486864014242, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.43)
43% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (8, 3), heading: (-1, 0), action: None, reward: 2.44320534201
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 15, 't': 20, 'action': None, 'reward': 2.44320534201174, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.44)
40% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: left, reward: 2.05965103445
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 21, 'action': 'left', 'reward': 2.059651034447224, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.06)
37% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: left, reward: 1.79854455476
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 13, 't': 22, 'action': 'left', 'reward': 1.7985445547642567, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.80)
34% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 243
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (4, 6), deadline = 30
Simulating trial. . . 
epsilon = 0.0261; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0261; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: forward, reward: 2.88138543462
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 30, 't': 0, 'action': 'forward', 'reward': 2.881385434619773, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.88)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: right, reward: 0.467424769907
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 29, 't': 1, 'action': 'right', 'reward': 0.4674247699074542, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.47)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: 1.91569975588
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.915699755881582, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.92)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: None, reward: 1.70067930616
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.700679306158188, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.70)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: left, reward: 1.01278108983
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 26, 't': 4, 'action': 'left', 'reward': 1.0127810898261498, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.01)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 2), heading: (-1, 0), action: forward, reward: 2.14877712219
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 2.1487771221900887, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.15)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: right, reward: 1.94730596472
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 24, 't': 6, 'action': 'right', 'reward': 1.9473059647197466, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.95)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: 2.47559446002
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 23, 't': 7, 'action': None, 'reward': 2.4755944600208686, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.48)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: None, reward: 2.44784864326
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.44784864326113, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.45)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: forward, reward: 2.08615179494
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 2.086151794937604, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.09)
67% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 244
\-------------------------

Environment.reset(): Trial set up with start = (3, 3), destination = (6, 6), deadline = 30
Simulating trial. . . 
epsilon = 0.0257; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 0.330524452201
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 30, 't': 0, 'action': None, 'reward': 0.33052445220142035, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.33)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 0.0302760316329
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'right'), 'deadline': 29, 't': 1, 'action': None, 'reward': 0.030276031632863964, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.03)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 2.06215419138
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 2.0621541913830095, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.06)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 1.26398212505
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 27, 't': 3, 'action': 'right', 'reward': 1.2639821250519474, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.26)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: 0.856721363123
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 26, 't': 4, 'action': 'right', 'reward': 0.8567213631225009, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.86)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 2.74423217864
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 5, 'action': None, 'reward': 2.7442321786352206, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.74)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 2.76443118663
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 24, 't': 6, 'action': None, 'reward': 2.764431186629482, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.76)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: right, reward: 1.77771619829
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 1.7777161982941316, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.78)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 2.38308822928
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 2.383088229284117, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 2.38)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 2.01840137262
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 2.01840137261724, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.02)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: forward, reward: 2.21556185445
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 2.215561854445636, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.22)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: None, reward: 2.66236336175
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 11, 'action': None, 'reward': 2.662363361751056, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.66)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 0.555569970928
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 18, 't': 12, 'action': 'right', 'reward': 0.5555699709275962, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.56)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: left, reward: 2.68753576773
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 2.6875357677275016, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.69)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (6, 2), heading: (0, -1), action: left, reward: 1.31222040727
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 16, 't': 14, 'action': 'left', 'reward': 1.3122204072741197, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 1.31)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: forward, reward: 2.1331385621
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 15, 'action': 'forward', 'reward': 2.1331385621025163, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.13)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 1.82651934484
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 14, 't': 16, 'action': None, 'reward': 1.82651934483549, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.83)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: 1.01035925884
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 13, 't': 17, 'action': None, 'reward': 1.0103592588361119, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.01)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: right, reward: -20.0158331031
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 3, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 12, 't': 18, 'action': 'right', 'reward': -20.01583310311282, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent attempted driving right through traffic and cause a minor accident. (rewarded -20.02)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 7), heading: (0, -1), action: None, reward: -5.03257267796
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 11, 't': 19, 'action': None, 'reward': -5.032572677955837, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent idled at a green light with no oncoming traffic. (rewarded -5.03)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: forward, reward: 1.36285253044
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 10, 't': 20, 'action': 'forward', 'reward': 1.3628525304363728, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.36)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 245
\-------------------------

Environment.reset(): Trial set up with start = (3, 3), destination = (7, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.0253; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 1.97304232862
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.973042328618529, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.97)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 2.46327722677
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 29, 't': 1, 'action': None, 'reward': 2.4632772267679526, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.46)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: None, reward: 2.93892278225
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 28, 't': 2, 'action': None, 'reward': 2.938922782246487, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.94)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: left, reward: 1.39981319661
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 27, 't': 3, 'action': 'left', 'reward': 1.3998131966066854, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.40)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 2.83719324157
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 26, 't': 4, 'action': None, 'reward': 2.837193241572942, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.84)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 2.36407239492
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 25, 't': 5, 'action': None, 'reward': 2.364072394918052, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.36)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: left, reward: 1.19338157932
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 24, 't': 6, 'action': 'left', 'reward': 1.1933815793160232, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.19)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: forward, reward: 1.64623542645
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 1.6462354264524193, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.65)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: None, reward: 1.37483701782
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 22, 't': 8, 'action': None, 'reward': 1.3748370178179241, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.37)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 2.75629671876
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 2.756296718757514, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.76)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 2.42257880465
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 2.422578804653415, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.42)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: 1.60058786
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 1.6005878599962804, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.60)
60% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 246
\-------------------------

Environment.reset(): Trial set up with start = (8, 4), destination = (1, 7), deadline = 20
Simulating trial. . . 
epsilon = 0.0250; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 2.68211149293
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.6821114929307472, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.68)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 2.48749106527
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.487491065267695, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.49)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: left, reward: 2.19799821512
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 2.1979982151172783, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.20)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: 2.49840892337
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 2.4984089233730424, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.50)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: right, reward: 1.17121285672
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.17121285671691, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.17)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 7), heading: (0, -1), action: left, reward: 1.761607947
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.7616079469994277, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.76)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: left, reward: 1.41230888518
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 14, 't': 6, 'action': 'left', 'reward': 1.4123088851818877, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.41)
65% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 247
\-------------------------

Environment.reset(): Trial set up with start = (6, 3), destination = (3, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0246; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: right, reward: 2.86904325173
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 2.869043251732678, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.87)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: right, reward: 1.46991400701
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 1.469914007009964, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.47)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: forward, reward: 0.976265985645
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 2, 'action': 'forward', 'reward': 0.9762659856452616, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.98)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 1.07475297618
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0747529761825168, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.07)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: right, reward: 0.705616719057
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 0.705616719057152, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.71)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: left, reward: 2.4263837507
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 2.4263837507035326, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.43)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.7128726738
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.7128726737956008, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.71)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 1.35940060368
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.3594006036826, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.36)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: 1.9753476475
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.9753476474973524, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.98)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: right, reward: 1.98256558615
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.982565586151069, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.98)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: None, reward: 1.58402216869
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 10, 't': 10, 'action': None, 'reward': 1.5840221686883027, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.58)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: left, reward: 2.1552404547
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 9, 't': 11, 'action': 'left', 'reward': 2.1552404546959067, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.16)
40% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 248
\-------------------------

Environment.reset(): Trial set up with start = (3, 2), destination = (8, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0242; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0242; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0242; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0242; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 3), heading: (0, 1), action: forward, reward: 0.249165981459
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 0.24916598145874058, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 0.25)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: right, reward: 1.79423663677
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.7942366367699376, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.79)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: None, reward: 1.87356503499
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.8735650349900415, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.87)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: right, reward: 0.673332262393
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 0.6733322623930118, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.67)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: left, reward: 1.92687744612
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.9268774461232623, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.93)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 7), heading: (0, -1), action: right, reward: 0.100238860251
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.10023886025118, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.10)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: left, reward: 1.3229065068
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.3229065067986054, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.32)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: right, reward: 1.80352317948
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 1.8035231794804862, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.80)
68% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 249
\-------------------------

Environment.reset(): Trial set up with start = (7, 4), destination = (3, 6), deadline = 30
Simulating trial. . . 
epsilon = 0.0239; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 1.53353206424
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.5335320642446846, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.53)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 2.3824919715
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 29, 't': 1, 'action': None, 'reward': 2.382491971504815, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.38)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: right, reward: 1.0907884522
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'right'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 1.090788452196973, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'right')
Agent drove right instead of left. (rewarded 1.09)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: left, reward: 0.527997542869
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 27, 't': 3, 'action': 'left', 'reward': 0.5279975428692923, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent drove left instead of right. (rewarded 0.53)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: forward, reward: 1.82422681585
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 1.8242268158457633, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.82)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: 2.03124536025
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'forward'), 'deadline': 25, 't': 5, 'action': None, 'reward': 2.0312453602463276, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.03)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: 1.71739798118
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 24, 't': 6, 'action': None, 'reward': 1.7173979811753513, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.72)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: forward, reward: 2.88370629803
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 23, 't': 7, 'action': 'forward', 'reward': 2.8837062980308232, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.88)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 2.44478342693
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 8, 'action': None, 'reward': 2.4447834269317195, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.44)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: None, reward: 2.75305557744
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 9, 'action': None, 'reward': 2.7530555774414562, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.75)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 1.1975842564
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 10, 'action': 'forward', 'reward': 1.197584256399548, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.20)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 1.06633338101
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 1.0663333810068585, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.07)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 0.972414914608
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 12, 'action': None, 'reward': 0.9724149146080425, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.97)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: None, reward: 2.32257979149
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 13, 'action': None, 'reward': 2.3225797914882937, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.32)
53% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: right, reward: 0.136086952202
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 16, 't': 14, 'action': 'right', 'reward': 0.13608695220158018, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.14)
50% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: 1.02971449071
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 15, 't': 15, 'action': 'right', 'reward': 1.0297144907054654, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 1.03)
47% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 0.864586556068
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 14, 't': 16, 'action': None, 'reward': 0.8645865560680006, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.86)
43% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: right, reward: 2.23158048684
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 13, 't': 17, 'action': 'right', 'reward': 2.231580486839439, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.23)
40% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 2), heading: (0, -1), action: right, reward: 0.941444616097
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 12, 't': 18, 'action': 'right', 'reward': 0.9414446160969447, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.94)
37% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: forward, reward: 2.35086156847
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 11, 't': 19, 'action': 'forward', 'reward': 2.3508615684710934, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.35)
33% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: forward, reward: 1.26664298045
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 10, 't': 20, 'action': 'forward', 'reward': 1.266642980445246, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 1.27)
30% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 250
\-------------------------

Environment.reset(): Trial set up with start = (8, 5), destination = (4, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.0235; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (1, 0), action: left, reward: 1.92866289144
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 30, 't': 0, 'action': 'left', 'reward': 1.9286628914433674, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.93)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: forward, reward: 1.12086120293
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 29, 't': 1, 'action': 'forward', 'reward': 1.1208612029324276, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.12)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 2.20010134308
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 28, 't': 2, 'action': None, 'reward': 2.200101343080844, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.20)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.96388260628
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 27, 't': 3, 'action': None, 'reward': 1.9638826062767814, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.96)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.40549306009
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 26, 't': 4, 'action': None, 'reward': 1.4054930600918167, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.41)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: forward, reward: 2.05567477356
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 2.055674773557644, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.06)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: forward, reward: 2.11940215139
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 2.1194021513857937, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.12)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 5), heading: (1, 0), action: None, reward: 0.00710735817686
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 23, 't': 7, 'action': None, 'reward': 0.007107358176863143, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.01)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 6), heading: (0, 1), action: right, reward: 0.908272040982
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 0.9082720409818748, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.91)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (0, 1), action: forward, reward: 1.29654844677
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 21, 't': 9, 'action': 'forward', 'reward': 1.2965484467694652, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.30)
67% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 251
\-------------------------

Environment.reset(): Trial set up with start = (4, 5), destination = (1, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.0232; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: right, reward: 1.46005765047
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.4600576504702902, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.46)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 2.9422211345
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.942221134502395, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.94)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.43933050051
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.4393305005100572, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.44)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.92559992936
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.9255999293618673, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.93)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: None, reward: 1.87571436896
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.8757143689617437, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.88)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: left, reward: 0.808132771838
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 0.8081327718375616, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.81)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 6), heading: (0, 1), action: None, reward: 1.52210669624
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.5221066962419982, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.52)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: right, reward: 2.72223765281
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 2.7222376528146333, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.72)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 6), heading: (-1, 0), action: None, reward: 1.34201975494
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.3420197549415485, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.34)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: forward, reward: 1.62607353588
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 1.6260735358784755, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.63)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: None, reward: 1.92711729841
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.9271172984051799, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.93)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: right, reward: 0.0110991380482
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 14, 't': 11, 'action': 'right', 'reward': 0.011099138048167645, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.01)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.06074768868
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 13, 't': 12, 'action': None, 'reward': 2.060747688681282, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.06)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: 0.879581547207
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 0.8795815472068091, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.88)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: 2.17103497799
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 11, 't': 14, 'action': 'left', 'reward': 2.171034977986173, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.17)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: right, reward: 1.45688861484
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 1.456888614843485, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.46)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 1.17504968313
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 1.1750496831302928, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 1.18)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 0.886978007274
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 8, 't': 17, 'action': 'right', 'reward': 0.8869780072740068, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 0.89)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.22839226559
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 7, 't': 18, 'action': None, 'reward': 1.2283922655910284, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.23)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.53451272972
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 6, 't': 19, 'action': None, 'reward': 1.534512729719816, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.53)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: None, reward: 1.36414542347
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 5, 't': 20, 'action': None, 'reward': 1.3641454234650856, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.36)
16% of time remaining to reach destination.

/-------------------
| Step 21 Results
\-------------------

Environment.step(): t = 21
Environment.act() [POST]: location: (1, 5), heading: (-1, 0), action: forward, reward: 2.014748112
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 4, 't': 21, 'action': 'forward', 'reward': 2.0147481120000887, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.01)
12% of time remaining to reach destination.

/-------------------
| Step 22 Results
\-------------------

Environment.step(): t = 22
Environment.act() [POST]: location: (1, 4), heading: (0, -1), action: right, reward: 0.354712636833
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 3, 't': 22, 'action': 'right', 'reward': 0.3547126368333149, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 0.35)
8% of time remaining to reach destination.

/-------------------
| Step 23 Results
\-------------------

Environment.step(): t = 23
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: right, reward: 0.78653188347
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 2, 't': 23, 'action': 'right', 'reward': 0.7865318834699917, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.79)
4% of time remaining to reach destination.

/-------------------
| Step 24 Results
\-------------------

Environment.step(): t = 24
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.887925366
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 1, 't': 24, 'action': None, 'reward': 1.8879253660027635, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.89)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 252
\-------------------------

Environment.reset(): Trial set up with start = (1, 5), destination = (6, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.0228; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0228; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 1.71593523131
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.7159352313055922, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 1.72)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 2.15847904875
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'left'), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.1584790487497827, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'left')
Agent properly idled at a red light. (rewarded 2.16)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: 1.71682906572
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.7168290657193825, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.72)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: right, reward: 0.630496672612
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 0.6304966726119323, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.63)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 6), heading: (-1, 0), action: right, reward: 1.47514444906
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 1.47514444906379, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.48)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: forward, reward: 2.12794892243
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.1279489224300803, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.13)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: 1.41272755448
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 1.4127275544784645, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.41)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 1.48297055001
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.4829705500070736, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.48)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 1.59124537871
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.591245378707159, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.59)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: right, reward: 1.71532107625
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 1.7153210762516127, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.72)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 1.27280892808
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.2728089280805, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 1.27)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: forward, reward: 1.8028693793
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.802869379295315, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', None)
Agent drove forward instead of left. (rewarded 1.80)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: None, reward: 1.70022316134
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.7002231613440417, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.70)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: left, reward: 2.62985120374
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'left', 'reward': 2.6298512037383914, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.63)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 4), heading: (-1, 0), action: forward, reward: 0.484680542298
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 11, 't': 14, 'action': 'forward', 'reward': 0.4846805422981658, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent drove forward instead of right. (rewarded 0.48)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: right, reward: 0.820036786447
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 0.8200367864466629, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 0.82)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: right, reward: 2.34268949954
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 9, 't': 16, 'action': 'right', 'reward': 2.3426894995433942, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.34)
32% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 253
\-------------------------

Environment.reset(): Trial set up with start = (5, 6), destination = (7, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0225; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: right, reward: 0.481123175182
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', 'left'), 'deadline': 20, 't': 0, 'action': 'right', 'reward': 0.481123175182395, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', 'left')
Agent drove right instead of left. (rewarded 0.48)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: right, reward: 2.53823942305
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 2.53823942305263, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.54)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: left, reward: 1.90815384889
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 1.9081538488860228, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 1.91)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: right, reward: 0.779552206183
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.7795522061829526, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.78)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: left, reward: 1.31309003752
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.3130900375209391, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.31)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: forward, reward: 1.91681264299
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'forward', 'reward': 1.9168126429883947, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.92)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 1.47187426077
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.471874260768236, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.47)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 2.71864528553
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.7186452855309926, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.72)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: None, reward: 2.52294057445
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.522940574445097, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.52)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 2.32866698134
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 11, 't': 9, 'action': 'forward', 'reward': 2.3286669813369745, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.33)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 3), heading: (0, -1), action: right, reward: 1.31418649201
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.3141864920093171, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.31)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: right, reward: 0.926222252016
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.9262222520157031, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.93)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 2.32369321347
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 2.3236932134735544, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.32)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: right, reward: 0.67307795467
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 7, 't': 13, 'action': 'right', 'reward': 0.6730779546702095, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 0.67)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: forward, reward: 1.06939843715
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 6, 't': 14, 'action': 'forward', 'reward': 1.0693984371544938, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.07)
25% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 254
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (3, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0221; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: forward, reward: 1.67164538389
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.6716453838893655, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.67)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: right, reward: 0.711441287984
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.7114412879836814, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.71)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: left, reward: 2.53621080116
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 18, 't': 2, 'action': 'left', 'reward': 2.536210801159581, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.54)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 6), heading: (-1, 0), action: left, reward: 2.26058286115
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 2.260582861146748, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.26)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: right, reward: 1.85234768683
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.8523476868325637, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.85)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 1.56434979744
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.5643497974438758, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.56)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 5), heading: (1, 0), action: right, reward: 0.01370441204
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 0.013704412040049574, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.01)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (0, 1), action: right, reward: 1.34479097993
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'right'), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.3447909799315463, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'right')
Agent followed the waypoint right. (rewarded 1.34)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: forward, reward: 1.2698223045
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', 'forward'), 'deadline': 12, 't': 8, 'action': 'forward', 'reward': 1.269822304500111, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', 'forward')
Agent drove forward instead of right. (rewarded 1.27)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: right, reward: 1.03909232063
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 11, 't': 9, 'action': 'right', 'reward': 1.0390923206285232, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.04)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: forward, reward: 1.34562521418
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 1.345625214182236, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.35)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: right, reward: 2.27948385297
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 2.2794838529746957, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.28)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: forward, reward: 1.14080615919
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', 'left'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 1.1408061591896348, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'left')
Agent followed the waypoint forward. (rewarded 1.14)
35% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 255
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (2, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0218; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: right, reward: 1.00263020171
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.0026302017090738, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.00)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: right, reward: 0.235147229881
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 0.2351472298805859, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.24)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: right, reward: 1.46291092375
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 1.4629109237526852, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.46)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 2.49326807581
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.493268075805549, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.49)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: None, reward: 2.62520407394
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.625204073938911, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.63)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 5), heading: (0, 1), action: left, reward: 2.84164850023
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 2.841648500231474, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.84)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: left, reward: 1.32188221267
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.3218822126692364, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.32)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 5), heading: (1, 0), action: None, reward: -4.21183452654
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 1, 'light': 'green', 'state': ('forward', 'green', 'forward', 'right'), 'deadline': 18, 't': 7, 'action': None, 'reward': -4.211834526544705, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', 'right')
Agent idled at a green light with no oncoming traffic. (rewarded -4.21)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 4), heading: (0, -1), action: left, reward: 0.0239279018935
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'right'), 'deadline': 17, 't': 8, 'action': 'left', 'reward': 0.023927901893522896, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'right')
Agent drove left instead of forward. (rewarded 0.02)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: right, reward: 1.49265583506
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'right'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 1.492655835056693, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'right')
Agent followed the waypoint right. (rewarded 1.49)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 1.14220035976
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 1.1422003597576733, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.14)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: forward, reward: 0.762771094554
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'right', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 0.7627710945542784, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'right', None)
Agent drove forward instead of right. (rewarded 0.76)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: right, reward: 2.14013534509
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 13, 't': 12, 'action': 'right', 'reward': 2.140135345085361, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 2.14)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 1.51410097763
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', 'forward'), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.514100977631772, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.51)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 5), heading: (0, 1), action: None, reward: 0.511166819509
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'left'), 'deadline': 11, 't': 14, 'action': None, 'reward': 0.5111668195091718, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 0.51)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 5), heading: (-1, 0), action: right, reward: 0.879597982021
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'left'), 'deadline': 10, 't': 15, 'action': 'right', 'reward': 0.8795979820209887, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'left')
Agent followed the waypoint right. (rewarded 0.88)
36% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 256
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (4, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0215; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: left, reward: 2.32230716538
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 25, 't': 0, 'action': 'left', 'reward': 2.32230716537973, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.32)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: None, reward: 2.87958366809
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.879583668087209, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.88)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (0, 1), action: None, reward: 2.07176045507
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.0717604550734996, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.07)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: left, reward: 1.21018095304
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 1.2101809530407988, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.21)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (0, 1), action: right, reward: 0.885587930205
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 21, 't': 4, 'action': 'right', 'reward': 0.8855879302051896, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.89)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: left, reward: 1.34880647543
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 1.3488064754328266, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.35)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 2), heading: (1, 0), action: forward, reward: 2.22307962228
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.223079622280724, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.22)
72% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 257
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (6, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0212; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0212; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0212; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0212; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: right, reward: 1.83746872424
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.8374687242355028, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.84)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 2.85226816879
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.8522681687856597, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.85)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 2.46649651769
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.46649651768948, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.47)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (0, 1), action: None, reward: 2.3562945237
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.3562945237044315, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.36)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: left, reward: 1.67403201448
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 21, 't': 4, 'action': 'left', 'reward': 1.6740320144770544, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.67)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: 2.64951747571
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.6495174757083175, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.65)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: None, reward: 0.400584476163
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'forward'), 'deadline': 19, 't': 6, 'action': None, 'reward': 0.40058447616265347, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 0.40)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: right, reward: 2.15720635324
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 2.1572063532350714, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 2.16)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: 2.78622852663
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.7862285266320894, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.79)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: 1.35498672124
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.354986721235387, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.35)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: None, reward: 1.85077602507
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.850776025068657, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.85)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 5), heading: (0, 1), action: forward, reward: 1.06909986201
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.069099862014503, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.07)
52% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 258
\-------------------------

Environment.reset(): Trial set up with start = (6, 7), destination = (7, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0209; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.56651335836
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.5665133583621569, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.57)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.21953632385
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.2195363238475128, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.22)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.11965455506
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.1196545550621637, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.12)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 1.00169587485
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.0016958748492357, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: 2.39727987156
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.3972798715619392, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.40)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: left, reward: 0.965478398858
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 0.9654783988583937, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.97)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 6), heading: (1, 0), action: right, reward: 1.16141231633
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.1614123163325705, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.16)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 6), heading: (1, 0), action: forward, reward: 1.79837308045
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 1.7983730804475146, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 1.80)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: left, reward: 0.864107002902
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 0.864107002901785, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.86)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 5), heading: (0, -1), action: None, reward: 1.66807393882
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.6680739388242927, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.67)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: right, reward: -0.0909514303069
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': -0.09095143030687958, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded -0.09)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 2.53704425603
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 11, 'action': None, 'reward': 2.5370442560349136, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.54)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 5), heading: (1, 0), action: None, reward: 1.45840076999
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.458400769992733, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.46)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: left, reward: 0.96267841716
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 7, 't': 13, 'action': 'left', 'reward': 0.9626784171602962, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.96)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: 0.617992989245
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 6, 't': 14, 'action': None, 'reward': 0.6179929892453266, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 0.62)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (2, 4), heading: (0, -1), action: None, reward: 2.40065007454
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.400650074540913, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.40)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: left, reward: 1.79042583009
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'left', 'reward': 1.7904258300921034, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.79)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: forward, reward: 0.335641885687
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 3, 't': 17, 'action': 'forward', 'reward': 0.33564188568730047, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.34)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.11462756544
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 2, 't': 18, 'action': None, 'reward': 1.1146275654377524, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.11)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 4), heading: (-1, 0), action: None, reward: 1.88116153714
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.8811615371399437, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.88)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Training trial 259
\-------------------------

Environment.reset(): Trial set up with start = (5, 3), destination = (3, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0205; alpha = 0.0150
Simulating trial. . . 
epsilon = 0.0205; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: None, reward: 2.90474188451
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.9047418845088506, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.90)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: None, reward: 1.97126337857
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.9712633785748528, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.97)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: None, reward: 1.29690931664
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.2969093166370385, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.30)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: left, reward: 1.79588686173
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 1.7958868617253163, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.80)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (3, 3), heading: (-1, 0), action: forward, reward: 2.82306355359
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 2.823063553594544, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.82)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (3, 4), heading: (0, 1), action: left, reward: 1.81531171971
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.8153117197076145, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.82)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: right, reward: 1.16027338352
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.160273383517367, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.16)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: left, reward: 1.32501924531
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 13, 't': 7, 'action': 'left', 'reward': 1.3250192453095697, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.33)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: None, reward: 2.72964836003
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 8, 'action': None, 'reward': 2.7296483600323995, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.73)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 5), heading: (1, 0), action: left, reward: 2.78501130223
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 2.78501130222723, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.79)
50% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 260
\-------------------------

Environment.reset(): Trial set up with start = (5, 2), destination = (3, 5), deadline = 25
Simulating trial. . . 
epsilon = 0.0202; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: forward, reward: 0.0975487445515
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'left'), 'deadline': 25, 't': 0, 'action': 'forward', 'reward': 0.09754874455147333, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'left')
Agent drove forward instead of right. (rewarded 0.10)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: right, reward: 2.00276525554
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'right'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 2.0027652555379403, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'right')
Agent followed the waypoint right. (rewarded 2.00)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 0.473992008078
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 0.4739920080779745, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.47)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 1.97437331468
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.9743733146780174, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.97)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: None, reward: 2.3369376748
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.336937674800471, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.34)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 0.478216243791
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.4782162437913916, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.48)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: left, reward: 1.97792303762
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 1.9779230376243488, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.98)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 1.63394903278
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.633949032779488, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.63)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 1.90624051445
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.9062405144456434, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.91)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: right, reward: 0.962370798358
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 0.9623707983578995, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent drove right instead of left. (rewarded 0.96)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 2.78513785669
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 15, 't': 10, 'action': None, 'reward': 2.7851378566853757, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.79)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: None, reward: 2.14685719024
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 14, 't': 11, 'action': None, 'reward': 2.1468571902425513, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 2.15)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: -0.0531479647521
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'left'), 'deadline': 13, 't': 12, 'action': 'right', 'reward': -0.053147964752143784, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'left')
Agent drove right instead of left. (rewarded -0.05)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: right, reward: 1.23136525299
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 12, 't': 13, 'action': 'right', 'reward': 1.2313652529929593, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.23)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 0.960220475743
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 11, 't': 14, 'action': 'right', 'reward': 0.9602204757429048, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.96)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 2.32067117731
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'left'), 'deadline': 10, 't': 15, 'action': None, 'reward': 2.3206711773125077, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 2.32)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: None, reward: 1.43986353612
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 9, 't': 16, 'action': None, 'reward': 1.4398635361154024, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.44)
32% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: left, reward: 2.3165030934
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 8, 't': 17, 'action': 'left', 'reward': 2.3165030934016597, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.32)
28% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 7), heading: (-1, 0), action: forward, reward: 0.60640446944
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 18, 'action': 'forward', 'reward': 0.6064044694396966, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.61)
24% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: right, reward: 0.914640266098
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 6, 't': 19, 'action': 'right', 'reward': 0.9146402660982238, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 0.91)
20% of time remaining to reach destination.

/-------------------
| Step 20 Results
\-------------------

Environment.step(): t = 20
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: forward, reward: 0.55792503553
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 5, 't': 20, 'action': 'forward', 'reward': 0.5579250355300294, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 0.56)
16% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Training trial 261
\-------------------------

Environment.reset(): Trial set up with start = (7, 3), destination = (4, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.0199; alpha = 0.0150

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (-1, 0), action: right, reward: 2.46060876
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 2.460608759999015, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 2.46)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: forward, reward: 1.38037507326
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 24, 't': 1, 'action': 'forward', 'reward': 1.3803750732623734, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.38)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: forward, reward: 2.34045775965
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': 2.340457759652482, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 2.34)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 1.13787900816
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 22, 't': 3, 'action': 'right', 'reward': 1.1378790081637198, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.14)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: forward, reward: 1.49020569312
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.4902056931197176, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.49)
80% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 1
\-------------------------

Environment.reset(): Trial set up with start = (1, 7), destination = (5, 3), deadline = 30
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.63360449204
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 30, 't': 0, 'action': None, 'reward': 1.6336044920428465, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.63)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.2907471281
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 29, 't': 1, 'action': None, 'reward': 1.2907471281047926, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.29)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: None, reward: 1.10241444939
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'left'), 'deadline': 28, 't': 2, 'action': None, 'reward': 1.10241444938905, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 1.10)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 7), heading: (-1, 0), action: forward, reward: 1.1788488504
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 27, 't': 3, 'action': 'forward', 'reward': 1.1788488503979222, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.18)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (-1, 0), action: forward, reward: 2.33718394492
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 26, 't': 4, 'action': 'forward', 'reward': 2.337183944922857, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.34)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 7), heading: (-1, 0), action: forward, reward: 2.65904437015
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 25, 't': 5, 'action': 'forward', 'reward': 2.659044370153898, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.66)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: left, reward: 1.9210384666
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'right'), 'deadline': 24, 't': 6, 'action': 'left', 'reward': 1.921038466603763, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'right')
Agent drove left instead of forward. (rewarded 1.92)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: right, reward: 1.73322515948
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 23, 't': 7, 'action': 'right', 'reward': 1.7332251594791694, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.73)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: left, reward: 1.55995220045
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 22, 't': 8, 'action': 'left', 'reward': 1.5599522004484712, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.56)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 2
\-------------------------

Environment.reset(): Trial set up with start = (5, 4), destination = (3, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: left, reward: 2.69445461938
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.6944546193776766, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.69)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: None, reward: 2.16490129129
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.1649012912944277, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.16)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: None, reward: 2.8810642251
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.881064225099715, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.88)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 3), heading: (-1, 0), action: left, reward: 2.94140238371
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 2.9414023837071506, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.94)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 2), heading: (0, -1), action: right, reward: 1.8825735625
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.8825735625011655, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 1.88)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 2), heading: (-1, 0), action: left, reward: 1.73920185537
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.7392018553678599, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.74)
70% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 3
\-------------------------

Environment.reset(): Trial set up with start = (8, 6), destination = (5, 2), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.74468277593
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.744682775931941, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.74)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.4074979276
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.407497927604904, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.41)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.38375372156
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.38375372156445, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.38)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 2.6658490329
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.665849032898994, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.67)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: 1.41514643673
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.4151464367281268, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.42)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: forward, reward: 1.57618171645
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 1.576181716446484, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.58)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: None, reward: 2.21292039284
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 2.212920392840048, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.21)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 6), heading: (-1, 0), action: forward, reward: 1.94891126995
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.9489112699544713, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.95)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: left, reward: 1.33707650499
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 17, 't': 8, 'action': 'left', 'reward': 1.3370765049851998, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.34)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 1.64759498806
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 16, 't': 9, 'action': None, 'reward': 1.6475949880567542, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.65)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 1.23331114347
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.2333111434716788, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.23)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 2.73507324682
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 14, 't': 11, 'action': None, 'reward': 2.735073246822068, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.74)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (5, 7), heading: (0, 1), action: None, reward: 1.18430106641
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.184301066414929, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.18)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (5, 2), heading: (0, 1), action: forward, reward: 1.32282619164
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 1.3228261916360207, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.32)
44% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 4
\-------------------------

Environment.reset(): Trial set up with start = (2, 6), destination = (4, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 1.30317298823
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'right'), 'deadline': 25, 't': 0, 'action': None, 'reward': 1.3031729882345506, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'right')
Agent properly idled at a red light. (rewarded 1.30)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 2.68858735707
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.688587357066984, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.69)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: None, reward: 1.2392348264
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.2392348264008126, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.24)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (3, 6), heading: (1, 0), action: forward, reward: 2.78323316468
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 2.783233164675554, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.78)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 6), heading: (1, 0), action: forward, reward: 1.1911534507
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.191153450701098, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 1.19)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: left, reward: 0.0966156542845
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 20, 't': 5, 'action': 'left', 'reward': 0.096615654284541, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.10)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: 2.22656235252
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.2265623525230462, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.23)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 3), heading: (0, -1), action: forward, reward: 1.7744454111
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.7744454111007337, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.77)
68% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 5
\-------------------------

Environment.reset(): Trial set up with start = (8, 4), destination = (2, 7), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: right, reward: 2.16986515417
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 2.1698651541684266, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 2.17)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.07736444312
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 2.077364443115069, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.08)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.62924326839
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.6292432683904046, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.63)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.2900988876
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 22, 't': 3, 'action': None, 'reward': 1.2900988876010413, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.29)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.32728159359
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', 'right'), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.327281593585175, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.33)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 2.5685463319
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.568546331901376, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.57)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (2, 5), heading: (0, 1), action: right, reward: 0.324799794006
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'right'), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 0.32479979400633463, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'right')
Agent drove right instead of left. (rewarded 0.32)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (2, 6), heading: (0, 1), action: forward, reward: 1.50176960117
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.501769601172555, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.50)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: forward, reward: 2.1863926095
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 17, 't': 8, 'action': 'forward', 'reward': 2.1863926094990433, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.19)
64% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 6
\-------------------------

Environment.reset(): Trial set up with start = (5, 2), destination = (1, 5), deadline = 35
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (1, 0), action: forward, reward: 2.47837091539
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 35, 't': 0, 'action': 'forward', 'reward': 2.4783709153932634, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.48)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: right, reward: 1.94047813061
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 34, 't': 1, 'action': 'right', 'reward': 1.9404781306109087, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.94)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 2.17446978886
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 33, 't': 2, 'action': None, 'reward': 2.1744697888577575, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.17)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (0, 1), action: None, reward: 2.08927963986
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 32, 't': 3, 'action': None, 'reward': 2.089279639860033, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.09)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: right, reward: -0.0093001289988
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 31, 't': 4, 'action': 'right', 'reward': -0.00930012899880217, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded -0.01)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: 1.0039255251
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 30, 't': 5, 'action': None, 'reward': 1.0039255250994286, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (5, 3), heading: (-1, 0), action: None, reward: 1.07236322396
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 29, 't': 6, 'action': None, 'reward': 1.0723632239591891, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.07)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 4), heading: (0, 1), action: left, reward: 1.5793837176
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 28, 't': 7, 'action': 'left', 'reward': 1.579383717597121, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.58)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: right, reward: 0.165365864543
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', 'right'), 'deadline': 27, 't': 8, 'action': 'right', 'reward': 0.1653658645426318, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', 'right')
Agent drove right instead of left. (rewarded 0.17)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 2.6361909575
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 26, 't': 9, 'action': None, 'reward': 2.6361909574980027, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.64)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (4, 4), heading: (-1, 0), action: None, reward: 1.45184827659
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 25, 't': 10, 'action': None, 'reward': 1.4518482765886296, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.45)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 4), heading: (-1, 0), action: forward, reward: 1.91698987013
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 24, 't': 11, 'action': 'forward', 'reward': 1.9169898701299275, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.92)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: right, reward: 1.40671631265
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 23, 't': 12, 'action': 'right', 'reward': 1.4067163126537179, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.41)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: left, reward: 2.66308714126
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 22, 't': 13, 'action': 'left', 'reward': 2.6630871412573653, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.66)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: forward, reward: 2.14553094676
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 21, 't': 14, 'action': 'forward', 'reward': 2.145530946764509, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.15)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: left, reward: 2.69933163296
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 15, 'action': 'left', 'reward': 2.6993316329636343, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.70)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: None, reward: 1.57837195387
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'forward'), 'deadline': 19, 't': 16, 'action': None, 'reward': 1.5783719538737597, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'forward')
Agent properly idled at a red light. (rewarded 1.58)
51% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 5), heading: (0, 1), action: forward, reward: 1.75219351942
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 18, 't': 17, 'action': 'forward', 'reward': 1.7521935194236375, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.75)
49% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 7
\-------------------------

Environment.reset(): Trial set up with start = (6, 4), destination = (2, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 3), heading: (0, -1), action: right, reward: 1.5864329591
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'left'), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.586432959099365, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'left')
Agent followed the waypoint right. (rewarded 1.59)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: right, reward: 1.6650651406
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.6650651405951244, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 1.67)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 2.28632521589
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 23, 't': 2, 'action': None, 'reward': 2.286325215885305, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.29)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 2.9081384386
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.908138438596041, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.91)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: None, reward: 1.06720928858
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.0672092885822555, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.07)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: forward, reward: 2.1882557921
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.188255792096066, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.19)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 4), heading: (0, 1), action: right, reward: 0.906897623641
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', 'forward'), 'deadline': 19, 't': 6, 'action': 'right', 'reward': 0.9068976236408194, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', 'forward')
Agent drove right instead of forward. (rewarded 0.91)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 4), heading: (-1, 0), action: right, reward: 1.66856332972
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 18, 't': 7, 'action': 'right', 'reward': 1.6685633297247862, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.67)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 3), heading: (0, -1), action: right, reward: 1.20212224883
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 1.2021222488276082, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.20)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: right, reward: 2.36988823947
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', 'forward'), 'deadline': 16, 't': 9, 'action': 'right', 'reward': 2.369888239474854, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', 'forward')
Agent followed the waypoint right. (rewarded 2.37)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: None, reward: 1.50424344622
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.5042434462236356, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.50)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: None, reward: 2.40284131134
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 11, 'action': None, 'reward': 2.4028413113442326, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.40)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: None, reward: 1.53868938923
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 13, 't': 12, 'action': None, 'reward': 1.5386893892291171, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.54)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: 2.08065799272
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 12, 't': 13, 'action': 'forward', 'reward': 2.080657992716841, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.08)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 1.27470894674
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', 'left'), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.2747089467412933, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', 'left')
Agent properly idled at a red light. (rewarded 1.27)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: None, reward: 2.6041608845
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 10, 't': 15, 'action': None, 'reward': 2.6041608844970607, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.60)
36% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (2, 3), heading: (1, 0), action: forward, reward: 1.11398235072
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 16, 'action': 'forward', 'reward': 1.1139823507184619, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.11)
32% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 8
\-------------------------

Environment.reset(): Trial set up with start = (5, 6), destination = (3, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: left, reward: 1.35821910329
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 1.358219103289071, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.36)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: 2.11303148652
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 19, 't': 1, 'action': None, 'reward': 2.1130314865150766, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.11)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: 1.971469247
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.9714692470018575, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.97)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: None, reward: 1.77984879326
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 17, 't': 3, 'action': None, 'reward': 1.7798487932595202, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 1.78)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: left, reward: 1.5024597611
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 16, 't': 4, 'action': 'left', 'reward': 1.5024597611029424, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.50)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: None, reward: 1.13448169095
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.1344816909511726, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.13)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: None, reward: 1.89238488851
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 14, 't': 6, 'action': None, 'reward': 1.8923848885103842, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.89)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 5), heading: (-1, 0), action: forward, reward: 2.73794674034
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 13, 't': 7, 'action': 'forward', 'reward': 2.7379467403396847, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.74)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 4), heading: (0, -1), action: right, reward: 1.00436812056
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': 'right', 'reward': 1.0043681205624915, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.00)
55% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 9
\-------------------------

Environment.reset(): Trial set up with start = (3, 3), destination = (6, 4), deadline = 20
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 3), heading: (1, 0), action: left, reward: 2.66368253174
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'left'), 'deadline': 20, 't': 0, 'action': 'left', 'reward': 2.6636825317368693, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'left')
Agent followed the waypoint left. (rewarded 2.66)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: forward, reward: 1.58682081848
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.586820818479571, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.59)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 3), heading: (1, 0), action: None, reward: 1.57087565387
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.570875653867057, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.57)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: forward, reward: 1.60194590923
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 1.6019459092257693, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.60)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 4), heading: (0, 1), action: right, reward: 2.27957610397
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 2.279576103973143, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 2.28)
75% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 10
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (8, 7), deadline = 30
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: left, reward: 2.3184638029
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 30, 't': 0, 'action': 'left', 'reward': 2.3184638028992097, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.32)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (2, 3), heading: (-1, 0), action: left, reward: 1.57618889411
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 29, 't': 1, 'action': 'left', 'reward': 1.5761888941101099, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.58)
93% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: right, reward: 0.4448573364
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 28, 't': 2, 'action': 'right', 'reward': 0.44485733639998715, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.44)
90% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: None, reward: 2.51950613873
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 27, 't': 3, 'action': None, 'reward': 2.5195061387259647, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.52)
87% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 2), heading: (0, -1), action: None, reward: 2.39027676797
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 26, 't': 4, 'action': None, 'reward': 2.3902767679691217, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.39)
83% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 2), heading: (-1, 0), action: left, reward: 1.97103635305
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 25, 't': 5, 'action': 'left', 'reward': 1.9710363530512496, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.97)
80% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: forward, reward: 2.8801247792
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 24, 't': 6, 'action': 'forward', 'reward': 2.880124779197229, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.88)
77% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (0, 1), action: left, reward: 0.219190655297
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'left'), 'deadline': 23, 't': 7, 'action': 'left', 'reward': 0.21919065529701542, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'left')
Agent drove left instead of right. (rewarded 0.22)
73% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 3), heading: (-1, 0), action: right, reward: 2.45081263945
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 22, 't': 8, 'action': 'right', 'reward': 2.4508126394481624, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.45)
70% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: right, reward: 2.71896421238
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 21, 't': 9, 'action': 'right', 'reward': 2.7189642123783475, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 2.72)
67% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 2), heading: (0, -1), action: None, reward: 0.0593621727637
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, 'forward'), 'deadline': 20, 't': 10, 'action': None, 'reward': 0.059362172763718135, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 0.06)
63% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: right, reward: 1.25345518239
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', None), 'deadline': 19, 't': 11, 'action': 'right', 'reward': 1.2534551823881646, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', None)
Agent followed the waypoint right. (rewarded 1.25)
60% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: None, reward: 2.37101955494
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 18, 't': 12, 'action': None, 'reward': 2.3710195549386817, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.37)
57% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (8, 7), heading: (0, -1), action: left, reward: 1.3682529564
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 13, 'action': 'left', 'reward': 1.368252956404178, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.37)
53% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 11
\-------------------------

Environment.reset(): Trial set up with start = (1, 6), destination = (3, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: right, reward: 0.73486982643
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 0.7348698264296258, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.73)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (8, 7), heading: (0, 1), action: left, reward: 2.56280973946
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 24, 't': 1, 'action': 'left', 'reward': 2.562809739455796, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.56)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: left, reward: 2.91864945808
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 23, 't': 2, 'action': 'left', 'reward': 2.9186494580844453, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.92)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 2.79861901149
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 22, 't': 3, 'action': None, 'reward': 2.7986190114921734, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.80)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 1.98063225986
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.9806322598559338, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.98)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 7), heading: (1, 0), action: forward, reward: 2.89878314775
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', None), 'deadline': 20, 't': 5, 'action': 'forward', 'reward': 2.8987831477484223, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', None)
Agent followed the waypoint forward. (rewarded 2.90)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: forward, reward: 2.75314835082
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 6, 'action': 'forward', 'reward': 2.7531483508187993, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.75)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (3, 7), heading: (1, 0), action: None, reward: 0.846611556656
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', 'left'), 'deadline': 18, 't': 7, 'action': None, 'reward': 0.8466115566562329, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', 'left')
Agent properly idled at a red light. (rewarded 0.85)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: right, reward: 1.10490801708
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'left', None), 'deadline': 17, 't': 8, 'action': 'right', 'reward': 1.1049080170834167, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'left', None)
Agent followed the waypoint right. (rewarded 1.10)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: None, reward: 2.7852084463
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 16, 't': 9, 'action': None, 'reward': 2.7852084463038436, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.79)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (3, 2), heading: (0, 1), action: None, reward: 1.45366263481
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.4536626348060517, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.45)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (2, 2), heading: (-1, 0), action: right, reward: -0.00736104386157
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 14, 't': 11, 'action': 'right', 'reward': -0.00736104386157177, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded -0.01)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: left, reward: 0.910008088849
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 0.9100080888486235, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 0.91)
48% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: 1.03339665822
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 12, 't': 13, 'action': None, 'reward': 1.0333966582231962, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.03)
44% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (2, 3), heading: (0, 1), action: None, reward: 1.22610460424
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 14, 'action': None, 'reward': 1.2261046042365302, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.23)
40% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 3), heading: (1, 0), action: left, reward: 1.37979649727
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 10, 't': 15, 'action': 'left', 'reward': 1.379796497266006, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.38)
36% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 12
\-------------------------

Environment.reset(): Trial set up with start = (7, 4), destination = (3, 3), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 2.47756407034
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 25, 't': 0, 'action': None, 'reward': 2.4775640703368107, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.48)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 1.1606034051
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 24, 't': 1, 'action': None, 'reward': 1.1606034050958203, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.16)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 1.59452696532
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 23, 't': 2, 'action': None, 'reward': 1.5945269653173169, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.59)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: left, reward: 2.28398345932
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 2.2839834593227026, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.28)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: forward, reward: 2.41025172256
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 2.4102517225648588, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.41)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.59231730474
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 20, 't': 5, 'action': None, 'reward': 1.5923173047435988, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.59)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 2.86989278702
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 2.869892787017778, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.87)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.35231532315
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 18, 't': 7, 'action': None, 'reward': 1.3523153231500311, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.35)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (1, 4), heading: (1, 0), action: None, reward: 1.42914056931
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.4291405693063028, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.43)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: forward, reward: 2.22180190179
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 2.2218019017897612, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.22)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (2, 4), heading: (1, 0), action: None, reward: 1.77203166683
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 15, 't': 10, 'action': None, 'reward': 1.7720316668280949, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.77)
56% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (3, 4), heading: (1, 0), action: forward, reward: 1.09696149305
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 14, 't': 11, 'action': 'forward', 'reward': 1.0969614930457734, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.10)
52% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 3), heading: (0, -1), action: left, reward: 0.997209062625
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 13, 't': 12, 'action': 'left', 'reward': 0.9972090626248, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.00)
48% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 13
\-------------------------

Environment.reset(): Trial set up with start = (6, 6), destination = (3, 5), deadline = 20
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 6), heading: (0, -1), action: None, reward: 2.87009282798
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.870092827977148, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 2.87)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: right, reward: 0.867436187238
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 19, 't': 1, 'action': 'right', 'reward': 0.8674361872378203, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.87)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (7, 6), heading: (1, 0), action: None, reward: 1.53060103528
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.5306010352844643, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 1.53)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: right, reward: 0.824324683227
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.8243246832271044, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.82)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 1.50931758964
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 16, 't': 4, 'action': None, 'reward': 1.5093175896417514, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.51)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (0, 1), action: None, reward: 1.12771385062
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 15, 't': 5, 'action': None, 'reward': 1.127713850624432, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.13)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: forward, reward: 0.0840521006618
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 14, 't': 6, 'action': 'forward', 'reward': 0.08405210066175428, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded 0.08)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 2.62699481015
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'left'), 'deadline': 13, 't': 7, 'action': None, 'reward': 2.6269948101532234, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 2.63)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 0.891073721333
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'right', None), 'deadline': 12, 't': 8, 'action': None, 'reward': 0.8910737213331805, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.89)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (0, 1), action: None, reward: 1.82164070344
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.821640703443871, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.82)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (8, 2), heading: (1, 0), action: left, reward: 2.03064710741
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 10, 't': 10, 'action': 'left', 'reward': 2.0306471074120305, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 2.03)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (1, 2), heading: (1, 0), action: forward, reward: 1.73914882775
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 1.7391488277470522, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.74)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (2, 2), heading: (1, 0), action: forward, reward: 1.07515949651
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'forward'), 'deadline': 8, 't': 12, 'action': 'forward', 'reward': 1.0751594965115554, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'forward')
Agent followed the waypoint forward. (rewarded 1.08)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (3, 2), heading: (1, 0), action: forward, reward: 0.711292648269
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 7, 't': 13, 'action': 'forward', 'reward': 0.7112926482690647, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 0.71)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: left, reward: 1.73399287907
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 6, 't': 14, 'action': 'left', 'reward': 1.7339928790738375, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 1.73)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (3, 7), heading: (0, -1), action: None, reward: 0.572617655033
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 0.5726176550333877, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.57)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: forward, reward: 2.1864409097
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': 2.1864409096979767, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 2.19)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 1.82367535823
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.8236753582322234, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.82)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (3, 6), heading: (0, -1), action: None, reward: 0.346671536186
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'left', None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.3466715361864412, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 0.35)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (3, 5), heading: (0, -1), action: forward, reward: 1.2081604213
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'left', None), 'deadline': 1, 't': 19, 'action': 'forward', 'reward': 1.2081604212957848, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'green', 'left', None)
Agent followed the waypoint forward. (rewarded 1.21)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Testing trial 14
\-------------------------

Environment.reset(): Trial set up with start = (2, 3), destination = (6, 6), deadline = 35
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 3), heading: (-1, 0), action: right, reward: 1.2798411215
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 35, 't': 0, 'action': 'right', 'reward': 1.2798411215028636, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.28)
97% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: right, reward: 1.3931532456
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'right', 'left'), 'deadline': 34, 't': 1, 'action': 'right', 'reward': 1.3931532456024835, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'right', 'left')
Agent drove right instead of forward. (rewarded 1.39)
94% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: 1.87793570574
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 33, 't': 2, 'action': None, 'reward': 1.8779357057376165, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.88)
91% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: 1.96935604128
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 32, 't': 3, 'action': None, 'reward': 1.9693560412800588, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.97)
89% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: None, reward: 2.59718924597
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 31, 't': 4, 'action': None, 'reward': 2.5971892459744983, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.60)
86% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: left, reward: 1.17277856699
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 30, 't': 5, 'action': 'left', 'reward': 1.1727785669859696, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.17)
83% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 2.53601362523
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 29, 't': 6, 'action': None, 'reward': 2.5360136252337586, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.54)
80% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 1.09726244698
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 28, 't': 7, 'action': None, 'reward': 1.0972624469809467, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.10)
77% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 2), heading: (-1, 0), action: None, reward: 2.62784297251
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 27, 't': 8, 'action': None, 'reward': 2.627842972506321, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.63)
74% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: forward, reward: 1.67409607539
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 26, 't': 9, 'action': 'forward', 'reward': 1.6740960753935445, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.67)
71% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 2), heading: (-1, 0), action: None, reward: 2.72123043278
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 25, 't': 10, 'action': None, 'reward': 2.721230432776965, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.72)
69% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 7), heading: (0, -1), action: right, reward: 1.11949459477
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 24, 't': 11, 'action': 'right', 'reward': 1.1194945947668664, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.12)
66% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (8, 7), heading: (1, 0), action: right, reward: 0.276708561249
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 23, 't': 12, 'action': 'right', 'reward': 0.27670856124898247, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.28)
63% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (8, 6), heading: (0, -1), action: left, reward: 1.76850041711
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 22, 't': 13, 'action': 'left', 'reward': 1.768500417111209, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 1.77)
60% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: left, reward: 1.47364406459
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 21, 't': 14, 'action': 'left', 'reward': 1.4736440645928586, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.47)
57% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: None, reward: 2.49622857086
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 20, 't': 15, 'action': None, 'reward': 2.4962285708601692, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.50)
54% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (6, 6), heading: (-1, 0), action: forward, reward: 1.52880425469
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 16, 'action': 'forward', 'reward': 1.528804254694813, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.53)
51% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 15
\-------------------------

Environment.reset(): Trial set up with start = (3, 4), destination = (1, 2), deadline = 20
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (2, 4), heading: (-1, 0), action: forward, reward: 1.71397778051
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 20, 't': 0, 'action': 'forward', 'reward': 1.7139777805144631, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.71)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 4), heading: (-1, 0), action: forward, reward: 1.28489420512
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 19, 't': 1, 'action': 'forward', 'reward': 1.2848942051242762, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.28)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 3), heading: (0, -1), action: right, reward: 1.75007897165
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 18, 't': 2, 'action': 'right', 'reward': 1.7500789716509693, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 1.75)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 2), heading: (0, -1), action: forward, reward: 2.51726985919
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 17, 't': 3, 'action': 'forward', 'reward': 2.5172698591926923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 2.52)
80% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 16
\-------------------------

Environment.reset(): Trial set up with start = (1, 7), destination = (6, 6), deadline = 20
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 2.34286264942
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 20, 't': 0, 'action': None, 'reward': 2.3428626494180773, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.34)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 1.59177208933
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.5917720893299745, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.59)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (1, 7), heading: (1, 0), action: None, reward: 2.14441066047
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 18, 't': 2, 'action': None, 'reward': 2.1444106604656605, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.14)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: left, reward: 2.51108782196
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 17, 't': 3, 'action': 'left', 'reward': 2.5110878219604285, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 2.51)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (2, 6), heading: (1, 0), action: right, reward: 1.37555982132
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 16, 't': 4, 'action': 'right', 'reward': 1.3755598213159108, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.38)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (2, 7), heading: (0, 1), action: right, reward: 2.70395610367
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', None, None), 'deadline': 15, 't': 5, 'action': 'right', 'reward': 2.703956103669997, 'waypoint': 'right'}
Agent previous state: ('right', 'red', None, None)
Agent followed the waypoint right. (rewarded 2.70)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (1, 7), heading: (-1, 0), action: right, reward: 2.53498780836
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, 'forward'), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 2.5349878083636312, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, 'forward')
Agent followed the waypoint right. (rewarded 2.53)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (1, 6), heading: (0, -1), action: right, reward: 0.490675590118
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'right', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', 'forward', None), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 0.49067559011783923, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', 'forward', None)
Agent drove right instead of forward. (rewarded 0.49)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: left, reward: 0.851806999608
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'left'), 'deadline': 12, 't': 8, 'action': 'left', 'reward': 0.8518069996076036, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'left')
Agent followed the waypoint left. (rewarded 0.85)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (8, 6), heading: (-1, 0), action: None, reward: 1.82276467732
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'left'), 'deadline': 11, 't': 9, 'action': None, 'reward': 1.8227646773224013, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'left')
Agent properly idled at a red light. (rewarded 1.82)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (7, 6), heading: (-1, 0), action: forward, reward: 2.49196574372
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 10, 't': 10, 'action': 'forward', 'reward': 2.491965743724246, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.49)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: right, reward: 0.231502267467
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 9, 't': 11, 'action': 'right', 'reward': 0.2315022674673033, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 0.23)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 1.01797435395
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 8, 't': 12, 'action': None, 'reward': 1.0179743539450221, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 1.02)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 1.23331894288
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.23331894287605, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 1.23)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 2.28859178962
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'right'), 'deadline': 6, 't': 14, 'action': None, 'reward': 2.288591789620517, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'right')
Agent properly idled at a red light. (rewarded 2.29)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (7, 5), heading: (0, -1), action: None, reward: 2.08414467828
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 5, 't': 15, 'action': None, 'reward': 2.0841446782796154, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.08)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: forward, reward: -0.488981631749
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', 'forward'), 'deadline': 4, 't': 16, 'action': 'forward', 'reward': -0.4889816317486204, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', 'forward')
Agent drove forward instead of left. (rewarded -0.49)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: None, reward: 0.998399773214
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 0.9983997732139975, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.00)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (7, 4), heading: (0, -1), action: None, reward: 0.230648498894
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.23064849889427697, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 0.23)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (6, 4), heading: (-1, 0), action: left, reward: 1.13493605665
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 1, 't': 19, 'action': 'left', 'reward': 1.1349360566462396, 'waypoint': 'left'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.13)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

/-------------------------
| Testing trial 17
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (7, 6), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (4, 7), heading: (0, -1), action: right, reward: 1.65239509612
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'right', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.6523950961228686, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'right', None)
Agent followed the waypoint right. (rewarded 1.65)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (1, 0), action: right, reward: 1.02968890679
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'left', None), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.0296889067949955, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'left', None)
Agent followed the waypoint right. (rewarded 1.03)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 7), heading: (1, 0), action: forward, reward: 2.89077222463
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 23, 't': 2, 'action': 'forward', 'reward': 2.8907722246271286, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.89)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: forward, reward: 0.971664618268
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 0.9716646182677342, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 0.97)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.20039015464
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', None), 'deadline': 21, 't': 4, 'action': None, 'reward': 2.2003901546362723, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', None)
Agent properly idled at a red light. (rewarded 2.20)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (7, 7), heading: (1, 0), action: None, reward: 2.32963964646
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'left', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'left', 'forward'), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.329639646462506, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'left', 'forward')
Agent properly idled at a red light. (rewarded 2.33)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (7, 6), heading: (0, -1), action: left, reward: 2.05307935204
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'left', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'left', None), 'deadline': 19, 't': 6, 'action': 'left', 'reward': 2.053079352036801, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'left', None)
Agent followed the waypoint left. (rewarded 2.05)
72% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 18
\-------------------------

Environment.reset(): Trial set up with start = (6, 7), destination = (4, 4), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (6, 2), heading: (0, 1), action: right, reward: 1.75315302775
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', None, None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 1.7531530277508642, 'waypoint': 'right'}
Agent previous state: ('right', 'green', None, None)
Agent followed the waypoint right. (rewarded 1.75)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 2), heading: (-1, 0), action: right, reward: 1.46968816473
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('right', 'red', 'forward', 'right'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 1.4696881647297761, 'waypoint': 'right'}
Agent previous state: ('right', 'red', 'forward', 'right')
Agent followed the waypoint right. (rewarded 1.47)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 7), heading: (0, -1), action: right, reward: 0.633177582925
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 23, 't': 2, 'action': 'right', 'reward': 0.6331775829254065, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.63)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: left, reward: 1.10509799918
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 22, 't': 3, 'action': 'left', 'reward': 1.105097999176287, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.11)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (4, 7), heading: (-1, 0), action: None, reward: 1.0694928214
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 21, 't': 4, 'action': None, 'reward': 1.0694928213968915, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.07)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: right, reward: 0.0740629212449
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'right', None), 'deadline': 20, 't': 5, 'action': 'right', 'reward': 0.07406292124493763, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'right', None)
Agent drove right instead of left. (rewarded 0.07)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 6), heading: (0, -1), action: None, reward: 1.16248369117
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.1624836911716716, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.16)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: forward, reward: 1.89302835649
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 18, 't': 7, 'action': 'forward', 'reward': 1.8930283564937946, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.89)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 2.76934364319
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 17, 't': 8, 'action': None, 'reward': 2.769343643192501, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 2.77)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (4, 5), heading: (0, -1), action: None, reward: 2.35617655368
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 16, 't': 9, 'action': None, 'reward': 2.3561765536844748, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.36)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: forward, reward: 0.951695254983
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 15, 't': 10, 'action': 'forward', 'reward': 0.9516952549834365, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 0.95)
56% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 19
\-------------------------

Environment.reset(): Trial set up with start = (4, 2), destination = (1, 4), deadline = 25
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 2), heading: (1, 0), action: right, reward: 0.794023863884
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 25, 't': 0, 'action': 'right', 'reward': 0.7940238638838766, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 0.79)
96% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 3), heading: (0, 1), action: right, reward: 0.0356307593243
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'left'), 'deadline': 24, 't': 1, 'action': 'right', 'reward': 0.03563075932427262, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'left')
Agent drove right instead of forward. (rewarded 0.04)
92% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: left, reward: 2.59129629087
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'forward'), 'deadline': 23, 't': 2, 'action': 'left', 'reward': 2.591296290869786, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'forward')
Agent followed the waypoint left. (rewarded 2.59)
88% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: forward, reward: 1.44424416478
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'forward'), 'deadline': 22, 't': 3, 'action': 'forward', 'reward': 1.4442441647798172, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'forward')
Agent followed the waypoint forward. (rewarded 1.44)
84% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: forward, reward: 1.06995700638
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 21, 't': 4, 'action': 'forward', 'reward': 1.069957006384854, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 1.07)
80% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: None, reward: 2.56436148151
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'forward', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 20, 't': 5, 'action': None, 'reward': 2.5643614815125133, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 2.56)
76% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: None, reward: 1.4155477778
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 19, 't': 6, 'action': None, 'reward': 1.415547777798526, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.42)
72% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: None, reward: 2.53706685408
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'right', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 18, 't': 7, 'action': None, 'reward': 2.537066854083524, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 2.54)
68% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (8, 3), heading: (1, 0), action: None, reward: 1.25389540301
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 17, 't': 8, 'action': None, 'reward': 1.2538954030078036, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.25)
64% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (1, 3), heading: (1, 0), action: forward, reward: 2.37093630487
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, None), 'deadline': 16, 't': 9, 'action': 'forward', 'reward': 2.3709363048656713, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, None)
Agent followed the waypoint forward. (rewarded 2.37)
60% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act(): Primary agent has reached destination!
Environment.act() [POST]: location: (1, 4), heading: (0, 1), action: right, reward: 2.74558998811
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', None), 'deadline': 15, 't': 10, 'action': 'right', 'reward': 2.7455899881059174, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', None)
Agent followed the waypoint right. (rewarded 2.75)
56% of time remaining to reach destination.

Trial Completed!
Agent reached the destination.

/-------------------------
| Testing trial 20
\-------------------------

Environment.reset(): Trial set up with start = (5, 7), destination = (3, 3), deadline = 20
Simulating trial. . . 
epsilon = 0.0000; alpha = 0.0000

/-------------------
| Step 0 Results
\-------------------

Environment.step(): t = 0
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 1.80359182124
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 20, 't': 0, 'action': None, 'reward': 1.8035918212413289, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.80)
95% of time remaining to reach destination.

/-------------------
| Step 1 Results
\-------------------

Environment.step(): t = 1
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 1.98278463115
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'right'), 'deadline': 19, 't': 1, 'action': None, 'reward': 1.9827846311474, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'right')
Agent properly idled at a red light. (rewarded 1.98)
90% of time remaining to reach destination.

/-------------------
| Step 2 Results
\-------------------

Environment.step(): t = 2
Environment.act() [POST]: location: (5, 7), heading: (-1, 0), action: None, reward: 1.48822979318
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', 'forward'), 'deadline': 18, 't': 2, 'action': None, 'reward': 1.4882297931792254, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', 'forward')
Agent properly idled at a red light. (rewarded 1.49)
85% of time remaining to reach destination.

/-------------------
| Step 3 Results
\-------------------

Environment.step(): t = 3
Environment.act() [POST]: location: (5, 6), heading: (0, -1), action: right, reward: 0.664249097389
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 17, 't': 3, 'action': 'right', 'reward': 0.6642490973889269, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 0.66)
80% of time remaining to reach destination.

/-------------------
| Step 4 Results
\-------------------

Environment.step(): t = 4
Environment.act() [POST]: location: (5, 5), heading: (0, -1), action: forward, reward: 1.3708753619
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', 'forward', 'left'), 'deadline': 16, 't': 4, 'action': 'forward', 'reward': 1.3708753618958953, 'waypoint': 'left'}
Agent previous state: ('left', 'green', 'forward', 'left')
Agent drove forward instead of left. (rewarded 1.37)
75% of time remaining to reach destination.

/-------------------
| Step 5 Results
\-------------------

Environment.step(): t = 5
Environment.act() [POST]: location: (4, 5), heading: (-1, 0), action: left, reward: 1.59145678269
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 15, 't': 5, 'action': 'left', 'reward': 1.5914567826891404, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.59)
70% of time remaining to reach destination.

/-------------------
| Step 6 Results
\-------------------

Environment.step(): t = 6
Environment.act() [POST]: location: (4, 4), heading: (0, -1), action: right, reward: 1.62113876659
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'forward', None), 'deadline': 14, 't': 6, 'action': 'right', 'reward': 1.6211387665921864, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'forward', None)
Agent drove right instead of forward. (rewarded 1.62)
65% of time remaining to reach destination.

/-------------------
| Step 7 Results
\-------------------

Environment.step(): t = 7
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: right, reward: 1.31792321557
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': 'right'}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, 'right'), 'deadline': 13, 't': 7, 'action': 'right', 'reward': 1.3179232155729923, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, 'right')
Agent drove right instead of left. (rewarded 1.32)
60% of time remaining to reach destination.

/-------------------
| Step 8 Results
\-------------------

Environment.step(): t = 8
Environment.act() [POST]: location: (5, 4), heading: (1, 0), action: None, reward: 1.35829753613
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'right'), 'deadline': 12, 't': 8, 'action': None, 'reward': 1.3582975361326595, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.36)
55% of time remaining to reach destination.

/-------------------
| Step 9 Results
\-------------------

Environment.step(): t = 9
Environment.act() [POST]: location: (5, 3), heading: (0, -1), action: left, reward: 1.86235757542
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 11, 't': 9, 'action': 'left', 'reward': 1.8623575754227448, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.86)
50% of time remaining to reach destination.

/-------------------
| Step 10 Results
\-------------------

Environment.step(): t = 10
Environment.act() [POST]: location: (6, 3), heading: (1, 0), action: right, reward: 1.7314082884
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'forward', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', 'forward', None), 'deadline': 10, 't': 10, 'action': 'right', 'reward': 1.7314082883983204, 'waypoint': 'left'}
Agent previous state: ('left', 'red', 'forward', None)
Agent drove right instead of left. (rewarded 1.73)
45% of time remaining to reach destination.

/-------------------
| Step 11 Results
\-------------------

Environment.step(): t = 11
Environment.act() [POST]: location: (7, 3), heading: (1, 0), action: forward, reward: 0.149660840301
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': 'forward', 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'green', 'state': ('right', 'green', 'forward', 'forward'), 'deadline': 9, 't': 11, 'action': 'forward', 'reward': 0.1496608403013302, 'waypoint': 'right'}
Agent previous state: ('right', 'green', 'forward', 'forward')
Agent drove forward instead of right. (rewarded 0.15)
40% of time remaining to reach destination.

/-------------------
| Step 12 Results
\-------------------

Environment.step(): t = 12
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: right, reward: 1.33520672836
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': 'forward', 'left': 'left'}, 'violation': 0, 'light': 'green', 'state': ('forward', 'green', None, 'left'), 'deadline': 8, 't': 12, 'action': 'right', 'reward': 1.3352067283642695, 'waypoint': 'forward'}
Agent previous state: ('forward', 'green', None, 'left')
Agent drove right instead of forward. (rewarded 1.34)
35% of time remaining to reach destination.

/-------------------
| Step 13 Results
\-------------------

Environment.step(): t = 13
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 1.59006964196
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, 'forward'), 'deadline': 7, 't': 13, 'action': None, 'reward': 1.590069641958314, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.59)
30% of time remaining to reach destination.

/-------------------
| Step 14 Results
\-------------------

Environment.step(): t = 14
Environment.act() [POST]: location: (7, 4), heading: (0, 1), action: None, reward: 1.63603634798
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('left', 'red', None, None), 'deadline': 6, 't': 14, 'action': None, 'reward': 1.6360363479838496, 'waypoint': 'left'}
Agent previous state: ('left', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.64)
25% of time remaining to reach destination.

/-------------------
| Step 15 Results
\-------------------

Environment.step(): t = 15
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: left, reward: 1.18487768093
Environment.act(): Step data: {'inputs': {'light': 'green', 'oncoming': None, 'right': None, 'left': None}, 'violation': 0, 'light': 'green', 'state': ('left', 'green', None, None), 'deadline': 5, 't': 15, 'action': 'left', 'reward': 1.184877680932442, 'waypoint': 'left'}
Agent previous state: ('left', 'green', None, None)
Agent followed the waypoint left. (rewarded 1.18)
20% of time remaining to reach destination.

/-------------------
| Step 16 Results
\-------------------

Environment.step(): t = 16
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.79410075691
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'forward'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'forward'), 'deadline': 4, 't': 16, 'action': None, 'reward': 1.7941007569097203, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, 'forward')
Agent properly idled at a red light. (rewarded 1.79)
15% of time remaining to reach destination.

/-------------------
| Step 17 Results
\-------------------

Environment.step(): t = 17
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.30519570973
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': 'left', 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, None), 'deadline': 3, 't': 17, 'action': None, 'reward': 1.3051957097348268, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', None, None)
Agent properly idled at a red light. (rewarded 1.31)
10% of time remaining to reach destination.

/-------------------
| Step 18 Results
\-------------------

Environment.step(): t = 18
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 0.808331823398
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': 'right', 'right': None, 'left': None}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', 'right', None), 'deadline': 2, 't': 18, 'action': None, 'reward': 0.8083318233983146, 'waypoint': 'forward'}
Agent previous state: ('forward', 'red', 'right', None)
Agent properly idled at a red light. (rewarded 0.81)
5% of time remaining to reach destination.

/-------------------
| Step 19 Results
\-------------------

Environment.step(): t = 19
Environment.act() [POST]: location: (8, 4), heading: (1, 0), action: None, reward: 1.35940149421
Environment.act(): Step data: {'inputs': {'light': 'red', 'oncoming': None, 'right': None, 'left': 'right'}, 'violation': 0, 'light': 'red', 'state': ('forward', 'red', None, 'right'), 'deadline': 1, 't': 19, 'action': None, 'reward': 1.3594014942137458, 'waypoint': 'forward'}
Environment.step(): Primary agent ran out of time! Trial aborted.
Agent previous state: ('forward', 'red', None, 'right')
Agent properly idled at a red light. (rewarded 1.36)
0% of time remaining to reach destination.

Trial Aborted!
Agent did not reach the destination.

Simulation ended. . .